legacy-archaeologist

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted codebase content, creating a surface for indirect prompt injection.\n
  • Ingestion points: Reads source files (src/), test files (tests/), and generated archaeology reports as part of the discovery and documentation process (SKILL.md).\n
  • Boundary markers: No specific delimiters or instructions to ignore instructions embedded within the analyzed source code are defined.\n
  • Capability inventory: The skill utilizes shell commands including grep, wc, test, git, and executes project-specific test runners like npm test or pytest.\n
  • Sanitization: There is no explicit sanitization or filtering of external code content before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to analyze the project and verify refactoring steps.\n
  • Evidence: Includes the use of grep, wc, test, and git log to extract system metadata and verify file integrity in the 'Self-Verification Checklist'.\n
  • Context: Commands are used for local static analysis and ensuring the consistency of the refactoring process.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 04:23 PM
Security Audit — agent-trust-hub — legacy-archaeologist