test-guide-from-code
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands including
git diff,gh pr diff, andglab mr diffto extract code changes and commit history for analysis. - [EXTERNAL_DOWNLOADS]: It fetches remote repository data from GitHub and GitLab via official CLI tools to support the analysis of Pull Requests and Merge Requests.
- [PROMPT_INJECTION]: The skill processes untrusted input from code diffs, creating a surface for indirect prompt injection.
- Ingestion points: Data is ingested through the output of git and repository CLI tools.
- Boundary markers: There are no explicit instructions to ignore instructions embedded in the analyzed code content.
- Capability inventory: The skill can execute read-only shell commands and perform file writes to the local directory.
- Sanitization: Content from diffs is analyzed directly without pre-processing or sanitization.
Audit Metadata