qstack-review
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository, including code changes and custom rules files, which could contain instructions to subvert the review process.\n
- Ingestion points: The skill reads full contents of changed files and repository-specific
CODE_REVIEW_RULES.mdfiles (SKILL.md).\n - Boundary markers: There are no explicit instructions for using delimiters to isolate untrusted content from the agent's system instructions (SKILL.md).\n
- Capability inventory: The skill's capabilities are restricted to textual analysis and reporting; it is explicitly forbidden from writing files, posting comments, or committing code (SKILL.md).\n
- Sanitization: No sanitization or verification of the repository content is specified before processing.
Audit Metadata