pr-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from pull requests, including source code, commit messages, and PR descriptions.
- Ingestion points: PR number, branch name, and ticket descriptions are used to fetch and analyze external data.
- Boundary markers: The skill lacks explicit delimiters or instructions to the agent to treat the PR content strictly as data, which could allow malicious instructions inside a PR to influence the agent's analysis.
- Capability inventory: While not explicitly listing tools, the skill requires the agent to read file contents and analyze git diffs.
- Sanitization: No sanitization or filtering of the processed PR data is specified in the instructions.
Audit Metadata