codebase-guide
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary functionality is restricted to reading local codebase files and writing a generated Markdown document to a local path. No malicious activity, obfuscation, or remote downloads were detected.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process untrusted data from an external repository.
- Ingestion points: The skill reads various files including package manifests, configuration files (e.g., .env.example), and source code during its 'Discovery' phase.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions that might be embedded within the comments or code of the analyzed files.
- Capability inventory: The skill allows the agent to create directories and write Markdown files to the local file system (defaulting to docs/CODEBASE_GUIDE.md).
- Sanitization: No sanitization or filtering logic is specified for the content read from the repository before it is analyzed and incorporated into the output document.
Audit Metadata