kernel-audit-review
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a well-defined manual review workflow. No malicious patterns, hardcoded credentials, or suspicious tool usage were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface because it reads and evaluates external data (files and diffs), which is necessary for its function as a review tool.
- Ingestion points: Reads project artifacts and diffs using the Read and Grep tools.
- Boundary markers: No specific instructions are provided to the agent to treat reviewed content as data rather than instructions.
- Capability inventory: The skill has access to Bash, Read, Grep, and Glob.
- Sanitization: No sanitization of the reviewed content is performed.
Audit Metadata