review
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process external data (code for review) which could contain malicious instructions.
- Ingestion point: The core instruction in
SKILL.mdto review code. - Boundary markers: Absent; no delimiters are defined to separate the reviewer instructions from the untrusted code content.
- Capability inventory: None; the skill contains no executable code, subprocess calls, or network operations.
- Sanitization: Absent; no validation or filtering of the input code is specified.
- [No Code] (SAFE): No executable scripts, binaries, or package dependencies were detected, significantly limiting the potential for exploitation via typical attack vectors like RCE or data exfiltration.
Audit Metadata