skills/identity16/skills/depth-check/Gen Agent Trust Hub

depth-check

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to query the local environment. Evidence: Step 4 describes using git log --author=<user email from git config> --oneline -- <path> to analyze commit history.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data which may contain malicious instructions. 1. Ingestion points: Git log output, file contents within the project blast radius, and user task descriptions. 2. Boundary markers: None identified; the instructions do not specify delimiters to separate untrusted content. 3. Capability inventory: The skill performs file system inspection and git history analysis. 4. Sanitization: No validation or sanitization of input data is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 05:29 AM