review-all
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized capabilities were detected in the skill instructions or associated scripts.
- [COMMAND_EXECUTION]: The skill executes local Git commands and a provided bash script to identify modified files. These commands are standard for development workflows and are used as intended for determining review scope.
- [PROMPT_INJECTION]: The skill handles untrusted data via code reviews, creating a surface for indirect prompt injection. 1. Ingestion points: Changed files identified in SKILL.md. 2. Boundary markers: None specified. 3. Capability inventory: Spawns specialized review agents using the Task tool. 4. Sanitization: None. This surface is characteristic of the skill's primary purpose and is not considered an active threat.
Audit Metadata