gc-review-im
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands to facilitate its review workflow.
- Evidence: Uses
git rev-parseandgit diffto identify changes in the repository. - Evidence: Uses
catandjqto read and validate JSON configuration files from.gc-review/config.jsonand~/.gc-review/config.json. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it analyzes untrusted content from source code files and git history.
- Ingestion points: Content of files identified as IM-relevant (SQL, Prisma, Python models, etc.) and git diff outputs.
- Boundary markers: Absent. The instructions do not provide delimiters or negative constraints to prevent the model from following natural language instructions found within the code comments or data structures being reviewed.
- Capability inventory: Local command execution (
git,cat), access to the local git repository history, and generation of compliance reports. - Sanitization: Absent. The skill processes raw strings from code changes directly through its analysis logic without escaping or filtering potential injection patterns.
Audit Metadata