audit-documentation-drift
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and process untrusted external data from software repositories, creating a surface for indirect prompt injection.
- Ingestion points: Project documentation, source code, and configuration files identified in SKILL.md.
- Boundary markers: None are defined in the instructions to separate audited data from agent instructions.
- Capability inventory: The agent is instructed to read files and perform "focused checks," which could include command execution via CLI tools.
- Sanitization: There are no instructions for sanitizing or escaping content retrieved from the audited files.
- [NO_CODE]: The skill package consists solely of markdown instructions and JSON evaluation cases. It does not include any standalone scripts, binaries, or automated installation steps.
Audit Metadata