chore: remove unused scan tools and dead error type (#327)

* chore: remove unused scan tools and dead error type

* chore(logs): redact base URL and target URL from preflight info logs

.claude/commands/debug.md

@@ -135,7 +135,6 @@ shannon <URL> <REPO> --pipeline-testing
 |-------------------|---------|------------|
 | `config` | Configuration file issues | No |
 | `network` | Connection/timeout issues | Yes |
-| `tool` | External tool (nmap, etc.) failed | Yes |
 | `prompt` | Claude SDK/API issues | Sometimes |
 | `filesystem` | File read/write errors | Sometimes |
 | `validation` | Deliverable validation failed | Yes (via retry) |

CLAUDE.md

@@ -137,7 +137,7 @@ Durable workflow orchestration with crash recovery, queryable progress, intellig
 - `apps/worker/src/temporal/shared.ts` — Types, interfaces, query definitions
 ### Five-Phase Pipeline
 
-1. **Pre-Recon** (`pre-recon`) — External scans (nmap, subfinder, whatweb) + source code analysis
+1. **Pre-Recon** (`pre-recon`) — Source code analysis to build the architectural baseline
 2. **Recon** (`recon`) — Attack surface mapping from initial findings
 3. **Vulnerability Analysis** (5 parallel agents) — injection, xss, auth, authz, ssrf
 4. **Exploitation** (5 parallel agents, conditional) — Exploits confirmed vulnerabilities
@@ -244,5 +244,4 @@ Package managers are configured with a minimum release age (7 days). Requires pn
 - **Worker not processing** — Check `docker ps --filter "name=shannon-worker-"`
 - **Reset state** — `./shannon stop --clean`
 - **Local apps unreachable** — Use `host.docker.internal` instead of `localhost`
-- **Missing tools** — Use `--pipeline-testing` to skip nmap/subfinder/whatweb (graceful degradation)
 - **Container permissions** — On Linux, may need `sudo` for docker commands

Dockerfile

@@ -13,44 +13,12 @@ RUN apk update && apk add --no-cache \
     curl \
     wget \
     ca-certificates \
-    # Network libraries for Go tools
-    libpcap-dev \
-    linux-headers \
     # Language runtimes
-    go \
     nodejs-22 \
     npm \
-    python3 \
-    py3-pip \
-    ruby \
-    ruby-dev \
-    # Security tools available in Wolfi
-    nmap \
     # Additional utilities
     bash
 
-# Set environment variables for Go
-ENV GOPATH=/go
-ENV PATH=$GOPATH/bin:/usr/local/go/bin:$PATH
-ENV CGO_ENABLED=1
-
-# Create directories
-RUN mkdir -p $GOPATH/bin
-
-# Install Go-based security tools
-RUN go install -v github.com/projectdiscovery/subfinder/v2/cmd/subfinder@v2.13.0
-# Install WhatWeb from release tarball (Ruby-based tool)
-RUN curl -sL https://github.com/urbanadventurer/WhatWeb/archive/refs/tags/v0.6.3.tar.gz | tar xz -C /opt && \
-    mv /opt/WhatWeb-0.6.3 /opt/whatweb && \
-    chmod +x /opt/whatweb/whatweb && \
-    gem install addressable -v 2.8.9 && \
-    echo '#!/bin/bash' > /usr/local/bin/whatweb && \
-    echo 'cd /opt/whatweb && exec ./whatweb "$@"' >> /usr/local/bin/whatweb && \
-    chmod +x /usr/local/bin/whatweb
-
-# Install Python-based tools
-RUN pip3 install --no-cache-dir schemathesis==4.13.0
-
 # Install pnpm
 RUN npm install -g pnpm@10.33.0
 
@@ -84,15 +52,10 @@ RUN apk update && apk add --no-cache \
     curl \
     ca-certificates \
     shadow \
-    # Network libraries (runtime)
-    libpcap \
-    # Security tools
-    nmap \
     # Language runtimes (minimal)
     nodejs-22 \
     npm \
     python3 \
-    ruby \
     # Chromium browser and dependencies for Playwright
     chromium \
     # Additional libraries Chromium needs
@@ -110,20 +73,6 @@ RUN apk update && apk add --no-cache \
     # Font rendering
     fontconfig
 
-# Copy Go binaries from builder
-COPY --from=builder /go/bin/subfinder /usr/local/bin/
-
-# Copy WhatWeb from builder
-COPY --from=builder /opt/whatweb /opt/whatweb
-COPY --from=builder /usr/local/bin/whatweb /usr/local/bin/whatweb
-
-# Install WhatWeb Ruby dependencies in runtime stage
-RUN gem install addressable -v 2.8.9
-
-# Copy Python packages from builder
-COPY --from=builder /usr/lib/python3.*/site-packages /usr/lib/python3.12/site-packages
-COPY --from=builder /usr/bin/schemathesis /usr/bin/
-
 # Create non-root user
 RUN addgroup -g 1001 pentest && \
     adduser -u 1001 -G pentest -s /bin/bash -D pentest

README.md

@@ -44,7 +44,6 @@ Shannon identified 20+ vulnerabilities in OWASP Juice Shop, including authentica
 - **Reproducible Proof-of-Concept Exploits**: The final report contains only proven, exploitable findings with copy-and-paste PoCs. Vulnerabilities that cannot be exploited are not reported.
 - **OWASP Vulnerability Coverage**: Identifies and validates Injection, XSS, SSRF, and Broken Authentication/Authorization, with additional categories in development.
 - **Code-Aware Dynamic Testing**: Analyzes source code to guide attack strategy, then validates findings with live browser and CLI-based exploits against the running application.
-- **Integrated Security Tooling**: Leverages Nmap, Subfinder, WhatWeb, and Schemathesis during reconnaissance and discovery phases.
 - **Parallel Processing**: Vulnerability analysis and exploitation phases run concurrently across all attack categories.
 
 ## Product Line
@@ -744,8 +743,7 @@ Shannon uses a multi-agent architecture that combines white-box source code anal
 ```
         ┌──────────────────────┐
         │   Pre-Reconnaissance │
-        │  (nmap, subfinder,   │
-        │  whatweb, code scan) │
+        │   (source code scan) │
         └──────────┬───────────┘
                    │
                    ▼
@@ -788,7 +786,7 @@ Each scan runs in its own ephemeral Docker container (`docker run --rm`) with a
 
 #### **Phase 1: Pre-Reconnaissance**
 
-External scanning using nmap, subfinder, and whatweb to fingerprint the target's infrastructure and tech stack. Simultaneously performs source code analysis to identify the application framework, entry points, and potential attack surface from the codebase.
+Performs source code analysis to identify the application framework, entry points, and potential attack surface from the codebase. Builds the foundational architectural intelligence that all subsequent agents depend on.
 
 #### **Phase 2: Reconnaissance**
 

SHANNON-PRO.md

@@ -147,7 +147,7 @@ This phase informs everything downstream. If the codebase uses an ORM with param
 
 ## Phase 2: Reconnaissance
 
-Bridges static and dynamic analysis using browser automation. The recon agent correlates code findings with the live application, validating that endpoints actually exist, mapping authentication flows, inventorying input vectors (URL parameters, POST fields, headers, cookies), and documenting the real authorization architecture. This phase may also integrate with infrastructure discovery tools including Nmap, Subfinder, and WhatWeb for network perimeter mapping.
+Bridges static and dynamic analysis using browser automation. The recon agent correlates code findings with the live application, validating that endpoints actually exist, mapping authentication flows, inventorying input vectors (URL parameters, POST fields, headers, cookies), and documenting the real authorization architecture.
 
 ## Phase 3: Vulnerability Analysis
 
@@ -194,7 +194,6 @@ This correlation means that a data flow vulnerability identified in static analy
 - **Fully Autonomous Operation:** Shannon Pro handles complex workflows including 2FA/TOTP logins and SSO (e.g., Sign in with Google) without human intervention. TOTP is handled via a dedicated MCP server tool.
 - **White-Box Awareness:** Unlike black-box scanners, Shannon Pro reads the source code to intelligently guide its attack strategy, combining code-level insight with runtime validation.
 - **Parallel Processing:** Vulnerability analysis and exploitation phases run concurrently across attack domains, with pipelined parallelism minimizing total execution time.
-- **Tool Orchestration:** Shannon Pro orchestrates existing security tools (e.g., Schemathesis for API testing, Nmap for network discovery) while adding LLM reasoning to interpret results.
 - **Configurable Login Flows:** Authentication configuration specifies login procedures and credentials, which are interpolated into agent prompts for authenticated testing.
 
 ---

apps/worker/prompts/exploit-injection.txt

@@ -182,17 +182,16 @@ For each root vulnerability in your plan, you will follow this systematic, four-
 ## **Strategic Tool Usage**
 Use the right tool for the job to ensure thoroughness.
 - **Use `curl` (Manual Probing) for:** Initial confirmation, simple UNION/Error-based injections, and crafting specific WAF bypasses.
-- **Use `sqlmap` (Automation) for:** Time-consuming blind injections, automating enumeration **after** manual confirmation, and as a final step to try a wide range of payloads when manual techniques are failing.
 
 ## **Persistence and Effort Allocation**
 Measure your effort using tool calls rather than time to ensure thorough testing:
 - **Initial Confirmation Phase:** Minimum 3 distinct payload attempts per vulnerability before concluding it's not exploitable
 - **Bypass Attempts:** If a vulnerability appears mitigated, try at least 8-10 different technique variations (encoding, syntax, comment styles, etc.) before concluding it's properly defended  
-- **Escalation Trigger:** If manual testing exceeds 10-12 tool calls without progress on a single vulnerability, escalate to automated tools (`sqlmap`) or Task Agent scripting
+- **Escalation Trigger:** If manual testing exceeds 10-12 tool calls without progress on a single vulnerability, escalate to Task Agent scripting
 - **Termination Criteria:** After systematic attempts with multiple different techniques → classify as appropriate level
   
 ## **Using the Task Agent for Custom Scripting**
-You must delegate every injection automation task to the Task Agent. Use manual `curl` or `sqlmap` runs for spot checks, then escalate to scripted payload loops handled by the Task Agent.
+You must delegate every injection automation task to the Task Agent. Use manual `curl` runs for spot checks, then escalate to scripted payload loops handled by the Task Agent.
 
 **TEMPLATE FOR SCRIPTING TASKS (REQUIRED):**
 "

apps/worker/prompts/pre-recon-code.txt

@@ -44,7 +44,7 @@ Downstream vulnerability analysis will cover these classes: {{VULN_CLASSES_TESTE
 
 **Phase Sequence:** **PRE-RECON (You)** → RECON → VULN ANALYSIS (5 agents) → EXPLOITATION (5 agents) → REPORTING
 
-**Your Input:** External scan results from pre-recon tools (nmap, subfinder, whatweb)
+**Your Input:** Target application source code in the working directory
 **Your Output:** `.shannon/deliverables/pre_recon_deliverable.md` (feeds all subsequent analysis phases)
 **Shared Intelligence:** You create the foundational intelligence baseline that all other agents depend on
 
@@ -79,7 +79,6 @@ You are the **Code Intelligence Gatherer** and **Architectural Foundation Builde
 
 <starting_context>
 - You are the **ENTRY POINT** of the comprehensive security assessment - no prior deliverables exist to read
-- External reconnaissance tools have completed and their results are available in the working environment
 - The target application source code has been cloned and is ready for analysis in the current directory
 - You must create the **foundational intelligence baseline** that all subsequent agents depend on
 - **CRITICAL:** This is the ONLY agent with full source code access - your completeness determines whether vulnerabilities are found

apps/worker/prompts/recon.txt

@@ -1,5 +1,5 @@
 <role>
-You are a world-class Reconnaissance Analyst and Attack Surface Mapper. Your mission is to conduct a thorough white-box analysis of the target application by correlating external scan data, live application behavior, and the full source code.
+You are a world-class Reconnaissance Analyst and Attack Surface Mapper. Your mission is to conduct a thorough white-box analysis of the target application by correlating live application behavior with the full source code.
 </role>
 
 <objective>
@@ -7,7 +7,7 @@ Your goal is to create a comprehensive, structured map of the application's atta
 </objective>
 
 <starting_context>
-Your analysis must begin by reading and fully comprehending the initial intelligence report located at `.shannon/deliverables/pre_recon_deliverable.md`. This file contains the output of initial nmap, subfinder, whatweb, and code analysis scans. This is your only starting information.
+Your analysis must begin by reading and fully comprehending the initial intelligence report located at `.shannon/deliverables/pre_recon_deliverable.md`. This file contains the initial source code analysis. This is your only starting information.
 </starting_context>
 
 <target>
@@ -88,13 +88,13 @@ Please use these tools for the following use cases:
 
 **Phase Sequence:** PRE-RECON (Complete) → **RECONNAISSANCE (You)** → VULN ANALYSIS (5 agents) → EXPLOITATION (5 agents) → FINAL REPORT (next phase)
 
-**Your Input:** `.shannon/deliverables/pre_recon_deliverable.md` (external scan data, initial code analysis)
+**Your Input:** `.shannon/deliverables/pre_recon_deliverable.md` (initial code analysis)
 **Your Output:** `.shannon/deliverables/recon_deliverable.md` (comprehensive attack surface map)
 **Shared Intelligence:** None (you are the first analysis specialist)
 
 **WHAT HAPPENED BEFORE YOU:**
-- Pre-reconnaissance agent performed external scans (nmap, subfinder, whatweb) and initial code analysis
-- All attack surfaces, technologies, and entry points were catalogued from external perspective
+- Pre-reconnaissance agent performed initial source code analysis
+- Attack surfaces, technologies, and entry points were catalogued from the codebase
 
 **WHAT HAPPENS AFTER YOU:**
 - Injection Analysis specialist will analyze SQL injection and command injection vulnerabilities using your attack surface map
@@ -120,7 +120,7 @@ You must follow this methodical four-step process:
 
 1.  **Synthesize Initial Data:**
     - Read the entire `.shannon/deliverables/pre_recon_deliverable.md`.
-    - In your thoughts, create a preliminary list of known technologies, subdomains, open ports, and key code modules.
+    - In your thoughts, create a preliminary list of known technologies and key code modules.
 
 2.  **Interactive Application Exploration:**
     - Invoke the `playwright-cli` skill, then use it with `-s={{PLAYWRIGHT_SESSION}}` to navigate to the target.
@@ -174,8 +174,6 @@ A brief overview of the application's purpose, core technology stack (e.g., Next
 - **Frontend:** [Framework, key libraries, authentication libraries]
 - **Backend:** [Language, framework, key dependencies]
 - **Infrastructure:** [Hosting provider, CDN, database type]
-- **Identified Subdomains:** [List from subfinder and any others discovered]
-- **Open Ports & Services:** [List from nmap and their purpose]
 
 ## 3. Authentication & Session Management Flow
 - **Entry Points:** [e.g., /login, /register, /auth/sso]

apps/worker/prompts/report-executive.txt

@@ -12,7 +12,7 @@ Technical leadership (CTOs, CISOs, Engineering VPs) who need both technical accu
 The orchestrator has already concatenated all per-class deliverables into `comprehensive_security_assessment_report.md`. Each per-class section is either exploit-agent-produced exploitation evidence (when exploitation ran) or deterministically rendered findings from analysis-phase queues (when exploitation was disabled). The cleanup rules below apply uniformly to either source.
 Your task is to:
 1. Read this existing concatenated report
-2. Add Executive Summary (vulnerability overview) and Network Reconnaissance (security-relevant scan findings) sections at the top
+2. Add an Executive Summary (vulnerability overview) at the top
 3. Clean up ALL per-class report sections by removing extraneous content
 4. Save the modified version back to the same file
 
@@ -65,19 +65,10 @@ MODIFY the existing file `.shannon/deliverables/comprehensive_security_assessmen
 
 {{VULN_SUMMARY_SUBSECTIONS}}
 
-## Network Reconnaissance
-{Extract security-relevant findings from automated scanning tools:
-- Open ports and exposed services from nmap
-- Subdomain discoveries from subfinder that could expand attack surface
-- Security headers or misconfigurations detected by whatweb
-- Any other security-relevant findings from the automated tools
-SKIP stack details - technical leaders know their infrastructure}
-
 2. KEEPING the existing per-class report sections but CLEANING them according to the rules below
 
 3. The final structure should be:
    - Executive Summary (new)
-   - Network Reconnaissance (new)
    - All existing per-class report sections (cleaned)
 
 IMPORTANT: Do NOT reorder the existing per-class report sections. Maintain the exact order they appear in the concatenated report. Only remove sections that do not match the defined criteria above.
@@ -86,15 +77,12 @@ IMPORTANT: Do NOT reorder the existing per-class report sections. Maintain the e
 
 <instructions>
 1. Read the pre_recon and recon deliverable files to gather security-relevant information:
-   - Focus on findings from automated tools (nmap, subfinder, whatweb) that indicate security risks
-   - Note exposed services, open ports, subdomains, security misconfigurations
    - Skip basic information such as technology stack information (the team knows their own stack)
    - Use technical leadership tone - precise but concise
    - Use the current date for the assessment date
 
-2. Create the Executive Summary and Network Reconnaissance content:
+2. Create the Executive Summary content:
    - Executive Summary: Technical overview with actionable findings for engineering leaders
-   - Network Reconnaissance: Focus on security-relevant discoveries from automated scans
 
 3. Clean the per-class report sections in `.shannon/deliverables/comprehensive_security_assessment_report.md` by applying these rules:
    - KEEP these specific section headings:

apps/worker/src/services/preflight.ts

@@ -270,7 +270,7 @@ async function validateCredentials(logger: ActivityLogger, apiKey?: string, prov
   // 1. Custom base URL — validate endpoint is reachable via SDK query
   if (process.env.ANTHROPIC_BASE_URL && process.env.ANTHROPIC_AUTH_TOKEN) {
     const baseUrl = process.env.ANTHROPIC_BASE_URL;
-    logger.info(`Validating custom base URL: ${baseUrl}`);
+    logger.info('Validating custom base URL');
 
     try {
       for await (const message of query({ prompt: 'hi', options: { model: resolveModel('small'), maxTurns: 1 } })) {
@@ -454,7 +454,7 @@ function httpHead(url: string, timeoutMs: number): Promise<number> {
 
 /** Check that the target URL is reachable from inside the container. */
 async function validateTargetUrl(targetUrl: string, logger: ActivityLogger): Promise<Result<void, PentestError>> {
-  logger.info('Checking target URL reachability...', { targetUrl });
+  logger.info('Checking target URL reachability...');
 
   // 1. Parse URL
   let parsed: URL;

apps/worker/src/types/errors.ts

@@ -11,7 +11,7 @@
 /**
  * Specific error codes for reliable classification.
  *
- * ErrorCode provides precision within the coarse 8-category PentestErrorType.
+ * ErrorCode provides precision within the coarse 7-category PentestErrorType.
  * Used by classifyErrorForTemporal for code-based classification (preferred)
  * with string matching as fallback for external errors.
  */
@@ -47,15 +47,7 @@ export enum ErrorCode {
   BILLING_ERROR = 'BILLING_ERROR',
 }
 
-export type PentestErrorType =
-  | 'config'
-  | 'network'
-  | 'tool'
-  | 'prompt'
-  | 'filesystem'
-  | 'validation'
-  | 'billing'
-  | 'unknown';
+export type PentestErrorType = 'config' | 'network' | 'prompt' | 'filesystem' | 'validation' | 'billing' | 'unknown';
 
 export interface PentestErrorContext {
   [key: string]: unknown;