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, and glab mr diff to 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
Risk Level
SAFE
Analyzed
Jun 25, 2026, 07:19 AM
Security Audit — agent-trust-hub — test-guide-from-code