code-reading-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of repository files, folder trees, and user notes, which could contain malicious instructions designed to influence the agent's reporting or behavior.
- Ingestion points: Repository access, file tree analysis, and pasted codebase files as specified in the 'What to ask for' section of SKILL.md.
- Boundary markers: Absent; the instructions do not require the agent to use delimiters or explicitly ignore instructions embedded within analyzed code.
- Capability inventory: The skill includes instructions to save generated notes to connected external note-taking tools or 'Scratchpad connectors' (SKILL.md).
- Sanitization: Absent; there are no instructions to sanitize or escape content extracted from the analyzed codebase before inclusion in the final report.
Audit Metadata