code-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data which presents a surface for indirect prompt injection.
- Ingestion points: The skill processes pull requests and code diffs provided as input to the agent (identified in
SKILL.md). - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the code comments or logic of the diffs being reviewed.
- Capability inventory: The skill utilizes shell-based tools for linting, type checking, and secret scanning, which could be targeted by malicious code in the diffs.
- Sanitization: The instructions do not specify any sanitization or filtering of the code content before analysis.
Audit Metadata