swe-codebase-reverse-engineering

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external, undocumented codebases. This creates a surface for indirect prompt injection where malicious instructions hidden in the codebase's comments, string literals, or logic could attempt to subvert the agent's instructions during the analysis process.
  • Ingestion points: The agent reads source code, tests, and configuration files from a target codebase.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing untrusted code content.
  • Capability inventory: The agent is authorized to write documentation to the docs/ directory.
  • Sanitization: There are no requirements for sanitizing or escaping the content extracted from the codebase before it is used in documentation generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:57 AM
Security Audit — agent-trust-hub — swe-codebase-reverse-engineering