ai-audit
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted source code from the repository being audited.
- Ingestion points: In Phases 1 and 2 (SKILL.md), the agent reads source code at user-defined paths to identify AI surfaces and perform security evaluations.
- Boundary markers: The instructions lack explicit delimiters or specific 'ignore' commands to ensure the agent treats audited code strictly as data rather than potential instructions.
- Capability inventory: The skill utilizes filesystem tools including Read, Write, Glob, and Grep.
- Sanitization: There is no documented logic for sanitizing or escaping the content read from source files before it is processed by the agent or subagents.
Audit Metadata