code-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code, diffs, and pull requests which are untrusted data sources that could contain malicious instructions.
- Ingestion points: The skill processes user-provided code, diffs, or pull request content as described in the frontmatter triggers and description.
- Boundary markers: The instructions do not include specific delimiters or 'ignore' directives to prevent the agent from following instructions embedded within the code comments or strings of the file being reviewed.
- Capability inventory: The skill does not request any tool permissions (e.g.,
allowed-tools) and does not perform file writes, network operations, or shell command executions. - Sanitization: No sanitization or escaping of the input code is defined in the instructions.
Audit Metadata