security-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill is designed to process untrusted data (user code for review), which is a surface for indirect prompt injection. However, since the skill has no executable capabilities or network access, the risk is negligible.\n
- Ingestion points: User-provided code snippets for review via instructions in SKILL.md.\n
- Boundary markers: Absent; instructions do not provide delimiters for user input.\n
- Capability inventory: None; no subprocesses, network calls, or file-write operations are defined.\n
- Sanitization: Not applicable as the skill performs only textual analysis.\n- [No Code] (SAFE): No scripts or external package configurations (e.g., package.json, requirements.txt) are included.
Audit Metadata