diff --git a/apps/worker/prompts/validate-authentication.txt b/apps/worker/prompts/validate-authentication.txt index 5fc5d1d..963a5d9 100644 --- a/apps/worker/prompts/validate-authentication.txt +++ b/apps/worker/prompts/validate-authentication.txt @@ -27,7 +27,11 @@ After verification confirms login_success, save the authenticated browser sessio Run this only when login_success is true. Skip it on failure. + +When the login attempt concludes, call the `submit_auth_result` tool to report the outcome. + + - Submit each field (username, password, captcha, TOTP) exactly once. -- Any rejection = auth error: return `login_success: false` and stop. Do not retry. +- Any rejection = auth error: call `submit_auth_result` with `login_success: false` and stop. Do not retry. diff --git a/apps/worker/prompts/vuln-auth.txt b/apps/worker/prompts/vuln-auth.txt index 36cbabd..f132452 100644 --- a/apps/worker/prompts/vuln-auth.txt +++ b/apps/worker/prompts/vuln-auth.txt @@ -210,7 +210,7 @@ The MCP SDK injects each tool's complete description and per-field guidance into - `set_findings_summary` and `set_strategic_intelligence` are required — call both before terminating. They produce the load-bearing content the downstream `exploit-auth` agent reads. - `set_safe_vectors` is recommended. An empty array is acceptable on runs with no validated-secure components, but explicit emission is preferred over skipping. -**Relationship to the exploitation queue:** The exploitation queue (`auth_exploitation_queue.json`) is captured automatically from your final structured output at session end. The 3 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. +**Relationship to the exploitation queue:** The exploitation queue (`auth_exploitation_queue.json`) is produced by calling the `submit_exploitation_queue` tool when your analysis is complete. The 3 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. @@ -220,7 +220,7 @@ The MCP SDK injects each tool's complete description and per-field guidance into 1. **Systematic Analysis:** ALL relevant API endpoints and user-facing features identified in the reconnaissance deliverable must be analyzed for AuthN/AuthZ flaws. 2. **Deliverable Emission:** Call the 3 MCP tools (`set_findings_summary`, `set_strategic_intelligence`, `set_safe_vectors`) exactly once each with their respective section content. `set_findings_summary` and `set_strategic_intelligence` are required; `set_safe_vectors` is recommended (an empty array is acceptable but explicit emission is preferred). -**Note:** The exploitation queue is captured automatically from your final structured output at session end — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. +**Note:** The exploitation queue is produced by calling the `submit_exploitation_queue` tool when your analysis is complete — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. **ONLY AFTER** both systematic analysis AND the required MCP tool calls have been completed, announce "**AUTH ANALYSIS COMPLETE**" and stop. diff --git a/apps/worker/prompts/vuln-authz.txt b/apps/worker/prompts/vuln-authz.txt index 2059801..0116dc4 100644 --- a/apps/worker/prompts/vuln-authz.txt +++ b/apps/worker/prompts/vuln-authz.txt @@ -289,7 +289,7 @@ The MCP SDK injects each tool's complete description and per-field guidance into - `set_findings_summary` and `set_strategic_intelligence` are required — call both before terminating. They produce the load-bearing content the downstream `exploit-authz` agent reads. - `set_safe_vectors` and `set_blind_spots` are recommended. Empty arrays are acceptable on runs with no validated-secure endpoints or no constraint gaps, but explicit emission is preferred over skipping. -**Relationship to the exploitation queue:** The exploitation queue (`authz_exploitation_queue.json`) is captured automatically from your final structured output at session end. The 4 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. +**Relationship to the exploitation queue:** The exploitation queue (`authz_exploitation_queue.json`) is produced by calling the `submit_exploitation_queue` tool when your analysis is complete. The 4 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. @@ -299,7 +299,7 @@ The MCP SDK injects each tool's complete description and per-field guidance into 1. **Todo Completion:** ALL tasks in your TodoWrite list must be marked as "completed". 2. **Deliverable Emission:** Call the 4 MCP tools (`set_findings_summary`, `set_strategic_intelligence`, `set_safe_vectors`, `set_blind_spots`) exactly once each with their respective section content. `set_findings_summary` and `set_strategic_intelligence` are required; `set_safe_vectors` and `set_blind_spots` are recommended (empty arrays acceptable but explicit emission is preferred). -**Note:** The exploitation queue is captured automatically from your final structured output at session end — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. +**Note:** The exploitation queue is produced by calling the `submit_exploitation_queue` tool when your analysis is complete — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. **ONLY AFTER** both todo completion AND the required MCP tool calls have been completed, announce "**AUTHORIZATION ANALYSIS COMPLETE**" and stop. diff --git a/apps/worker/prompts/vuln-injection.txt b/apps/worker/prompts/vuln-injection.txt index 464b7fb..b5c5ed9 100644 --- a/apps/worker/prompts/vuln-injection.txt +++ b/apps/worker/prompts/vuln-injection.txt @@ -300,7 +300,7 @@ The MCP SDK injects each tool's complete description and per-field guidance into - `set_findings_summary` and `set_strategic_intelligence` are required — call both before terminating. They produce the load-bearing content the downstream `exploit-injection` agent reads. - `set_safe_vectors` and `set_blind_spots` are recommended. Empty arrays are acceptable on runs with no validated-secure vectors or no constraint gaps, but explicit emission is preferred over skipping. -**Relationship to the exploitation queue:** The exploitation queue (`injection_exploitation_queue.json`) is captured automatically from your final structured output at session end. The 4 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. +**Relationship to the exploitation queue:** The exploitation queue (`injection_exploitation_queue.json`) is produced by calling the `submit_exploitation_queue` tool when your analysis is complete. The 4 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. @@ -310,7 +310,7 @@ The MCP SDK injects each tool's complete description and per-field guidance into 1. **Todo Completion:** ALL tasks in your TodoWrite list must be marked as "completed". 2. **Deliverable Emission:** Call the 4 MCP tools (`set_findings_summary`, `set_strategic_intelligence`, `set_safe_vectors`, `set_blind_spots`) exactly once each with their respective section content. `set_findings_summary` and `set_strategic_intelligence` are required; `set_safe_vectors` and `set_blind_spots` are recommended (empty arrays acceptable but explicit emission is preferred). -**Note:** The exploitation queue is captured automatically from your final structured output at session end — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. +**Note:** The exploitation queue is produced by calling the `submit_exploitation_queue` tool when your analysis is complete — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. **ONLY AFTER** both todo completion AND the required MCP tool calls have been completed, announce "**INJECTION ANALYSIS COMPLETE**" and stop. diff --git a/apps/worker/prompts/vuln-ssrf.txt b/apps/worker/prompts/vuln-ssrf.txt index 2776ea9..5f700ee 100644 --- a/apps/worker/prompts/vuln-ssrf.txt +++ b/apps/worker/prompts/vuln-ssrf.txt @@ -259,7 +259,7 @@ The MCP SDK injects each tool's complete description and per-field guidance into - `set_findings_summary` and `set_strategic_intelligence` are required — call both before terminating. They produce the load-bearing content the downstream `exploit-ssrf` agent reads. - `set_safe_vectors` is recommended. An empty array is acceptable on runs with no validated-secure components, but explicit emission is preferred over skipping. -**Relationship to the exploitation queue:** The exploitation queue (`ssrf_exploitation_queue.json`) is captured automatically from your final structured output at session end. The 3 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. +**Relationship to the exploitation queue:** The exploitation queue (`ssrf_exploitation_queue.json`) is produced by calling the `submit_exploitation_queue` tool when your analysis is complete. The 3 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. @@ -269,7 +269,7 @@ The MCP SDK injects each tool's complete description and per-field guidance into 1. **Systematic Analysis:** ALL relevant API endpoints and request-making features identified in the reconnaissance deliverable must be analyzed for SSRF vulnerabilities. 2. **Deliverable Emission:** Call the 3 MCP tools (`set_findings_summary`, `set_strategic_intelligence`, `set_safe_vectors`) exactly once each with their respective section content. `set_findings_summary` and `set_strategic_intelligence` are required; `set_safe_vectors` is recommended (an empty array is acceptable but explicit emission is preferred). -**Note:** The exploitation queue is captured automatically from your final structured output at session end — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. +**Note:** The exploitation queue is produced by calling the `submit_exploitation_queue` tool when your analysis is complete — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. **ONLY AFTER** both systematic analysis AND the required MCP tool calls have been completed, announce "**SSRF ANALYSIS COMPLETE**" and stop. diff --git a/apps/worker/prompts/vuln-xss.txt b/apps/worker/prompts/vuln-xss.txt index 52d5ea3..6caa31a 100644 --- a/apps/worker/prompts/vuln-xss.txt +++ b/apps/worker/prompts/vuln-xss.txt @@ -222,7 +222,7 @@ The MCP SDK injects each tool's complete description and per-field guidance into - `set_findings_summary` and `set_strategic_intelligence` are required — call both before terminating. They produce the load-bearing content the downstream `exploit-xss` agent reads. - `set_safe_vectors` and `set_blind_spots` are recommended. Empty arrays are acceptable on runs with no validated-secure vectors or no constraint gaps, but explicit emission is preferred over skipping. -**Relationship to the exploitation queue:** The exploitation queue (`xss_exploitation_queue.json`) is captured automatically from your final structured output at session end. The 4 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. +**Relationship to the exploitation queue:** The exploitation queue (`xss_exploitation_queue.json`) is produced by calling the `submit_exploitation_queue` tool when your analysis is complete. The 4 MCP tools produce the analysis deliverable Markdown; the structured-output queue is separate and follows the `exploitation_queue_format` schema documented above. @@ -232,7 +232,7 @@ COMPLETION REQUIREMENTS (ALL must be satisfied): 1. Systematic Analysis: ALL input vectors identified from the reconnaissance deliverable must be analyzed. 2. Deliverable Emission: Call the 4 MCP tools (`set_findings_summary`, `set_strategic_intelligence`, `set_safe_vectors`, `set_blind_spots`) exactly once each with their respective section content. `set_findings_summary` and `set_strategic_intelligence` are required; `set_safe_vectors` and `set_blind_spots` are recommended (empty arrays acceptable but explicit emission is preferred). -**Note:** The exploitation queue is captured automatically from your final structured output at session end — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. +**Note:** The exploitation queue is produced by calling the `submit_exploitation_queue` tool when your analysis is complete — separate from the MCP tools above. The analysis deliverable Markdown is rendered by the harness after your session ends from the MCP tool calls. ONLY AFTER both systematic analysis AND the required MCP tool calls have been completed, announce "XSS ANALYSIS COMPLETE" and stop.