property-test-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Command Execution (LOW): The skill executes
git diffto identify modified files in the repository. This is an expected behavior for a developer-oriented tool. - Indirect Prompt Injection (LOW): The skill ingests untrusted data by reading source code from the current branch.
- Ingestion points: Source files (.ts, .py, .rs) and git diff output.
- Boundary markers: Absent. There are no explicit instructions to ignore embedded prompts in the analyzed code.
- Capability inventory: File system read/write, git command execution.
- Sanitization: Absent. The skill extracts specifications directly from code/comments.
Audit Metadata