mirror of
https://github.com/KeygraphHQ/shannon.git
synced 2026-08-11 14:00:24 +02:00
ezl-keygraphandGitHub
1ce250d6a5
* feat(worker): record token, cache, and turn usage per agent * feat: replace model tiers with a single SHANNON_AI_MODEL across five providers * feat(cli): rebuild the setup wizard for provider and model selection * docs: document single-model selection and supported providers * feat(worker): use chat completions for OpenAI behind a custom base URL * feat: add SHANNON_AI_OPENAI_FORMAT to pick the wire API for OpenAI gateways * refactor(cli): drop endpoint path hints from the gateway format picker * feat(worker): enable pi in-session provider retry with retry-after backoff * refactor(worker): hand provider error classification to pi and drop the Anthropic ladders * refactor: remove the subscription retry preset and pipeline config section * fix(worker): validate Bedrock credentials with the same live probe as other providers * feat(worker): render the report from structured findings instead of agent-written markdown * fix(worker): dispose the credential probe session on every path * fix(worker): refuse to replace the assembled report with an empty one * refactor(worker): catch post-processing throws across the whole finalization block * revert(worker): drop the report zero-findings guard * docs(worker): correct the retry split and Bedrock credential claims * docs: regenerate llms-full.txt from current sources * feat(cli): build and run the npx flow from a clone * refactor(cli): flatten the setup summary output * feat(cli): reject runs with more than one provider configured * fix(worker): say a rejected bash call never ran * chore(cli): drop grok-4.3 and gpt-5.6-luna from the setup suggestions * feat(worker): capture structured finding locations for SARIF output * fix(worker): enumerate queue confidence so the report inherits it verbatim * feat(worker): give the reporting phase a mode-specific output schema * feat(worker): emit a SARIF 2.1.0 log for exploitative runs * fix(worker): correct SARIF locations and defer fingerprinting to the upload action * fix(worker): drop the confidence suffix from the analysis-mode summary list * feat(worker): give exploit findings a dedicated code location field * feat(worker): carry structured code locations from the vuln queue to the report * fix(worker): join code locations from the vuln queue instead of re-asking agents * fix(worker): spell out the finding_id to category mapping in the tool schema * feat: drop Google/Gemini as a supported AI provider * fix(worker): stop asking the report agent for code locations * docs: correct the provider list and drop the removed rate-limit settings * docs: add provider cyber safeguards and suggested models per provider * docs: document the SARIF output and the report rating thresholds
52 lines
2.4 KiB
Markdown
52 lines
2.4 KiB
Markdown
# Safety and Limitations
|
|
|
|
Read this before running Shannon in a new environment.
|
|
|
|
## Authorized Use Only
|
|
|
|
Shannon is designed for legitimate security auditing. You must have explicit written authorization from the owner of the target system before running Shannon.
|
|
|
|
Unauthorized scanning or exploitation of systems you do not own is illegal. Keygraph is not responsible for misuse of Shannon.
|
|
|
|
## Do Not Run on Production
|
|
|
|
Shannon is not a passive scanner. Exploitation agents actively execute attacks to confirm vulnerabilities. This can mutate application state and data.
|
|
|
|
Do not run Shannon against production systems. Use sandboxed, staging, or local development environments where data integrity is not a concern.
|
|
|
|
Potential mutative effects include:
|
|
|
|
- Creating new users
|
|
- Modifying or deleting data
|
|
- Compromising test accounts
|
|
- Triggering unintended side effects from injection attacks
|
|
- Generating unexpected outbound traffic
|
|
- Writing exploit artifacts to reports or deliverables
|
|
|
|
For maximum isolation, run Shannon inside a disposable virtual machine.
|
|
|
|
## LLM and Automation Caveats
|
|
|
|
- **Verification is required**: Shannon uses a proof-by-exploitation methodology, but final reports can still contain weakly supported or incorrect details. Human review is essential.
|
|
- **Model support**: Shannon is officially supported only with Claude models. Alternative models may be incomplete, inaccurate, or unstable.
|
|
- **Prompt injection risk**: Do not point Shannon at untrusted or adversarial codebases. AI-powered tools that read source code can be influenced by malicious repository content.
|
|
|
|
## Scope of Analysis
|
|
|
|
Shannon currently targets exploitable vulnerabilities in these classes:
|
|
|
|
- Broken Authentication
|
|
- Broken Authorization
|
|
- Injection
|
|
- Cross-Site Scripting
|
|
- Server-Side Request Forgery
|
|
|
|
Shannon's proof-by-exploitation model means it does not report issues it cannot actively exploit, such as many vulnerable dependency, insecure configuration, or broad policy findings.
|
|
|
|
For broader coverage, the Keygraph platform adds black-box and white-box agentic pentesting, graph-based static analysis, SCA reachability, secrets detection, business logic testing, remediation workflows, SLA tracking, and reporting dashboards.
|
|
|
|
## Cost and Performance
|
|
|
|
A full test run typically takes roughly 1 to 1.5 hours. LLM API costs vary by model pricing, target complexity, selected provider, and concurrency.
|
|
|