code-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data such as source code and pull request diffs. Malicious instructions embedded within comments or strings in the files being reviewed could potentially influence the agent's behavior or review conclusions.
- Ingestion points: Processes files in scope, PR diffs, and project content as described in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the analyzed code are defined in the instructions.
- Capability inventory: The skill instructions focus on generating structured text reports; there are no explicit instructions to execute subprocesses or perform network operations.
- Sanitization: No sanitization or validation of the input code is implemented.
Audit Metadata