double-knuth
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for a systematic two-pass code review process focusing on correctness, cross-file consistency, and documentation accuracy. It utilizes read-only tools such as git and grep to perform checks.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface as it processes untrusted repository content. Ingestion points: Entire file set or repository (SKILL.md). Boundary markers: Absent. Capability inventory: Read-only file system access (grep, git), tool invocation (/code-review), and sub-agent spawning. Sanitization: Absent. The risk is assessed as safe given the read-only nature of the operations.
Audit Metadata