game-reverse-document

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted code and comments from external repositories, which presents a surface for indirect prompt injection. Maliciously crafted code comments could attempt to influence the agent's behavior during the documentation process. Ingestion points: Source code read via 'Read', 'Glob', and 'Grep' tools (SKILL.md). Boundary markers: Not explicitly defined in the workflow instructions. Capability inventory: 'Write' and 'AskUserQuestion' tools (SKILL.md). Sanitization: No specific sanitization of the scanned code content is described. This is a potential risk inherent to the tool's primary purpose.
  • [DATA_EXFILTRATION]: The skill is granted access to read files across the project directory. While no network exfiltration patterns were found, the 'Read' tool could theoretically access sensitive files like credentials if they are present in the scanned directory. Users should ensure the provided path is scoped correctly.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:44 PM
Security Audit — agent-trust-hub — game-reverse-document