add-test-coverage
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes repository code and git diffs to generate new test files, creating a surface where malicious comments or code in the repository could potentially influence the agent's output.
- Ingestion points: The skill reads repository files and git diff outputs using
ReadandBash(git:diff)(Phase 1). - Boundary markers: None explicitly defined to separate untrusted repository content from instructions.
- Capability inventory: The skill is authorized to use git commands and write/modify files in the repository to implement tests.
- Sanitization: No explicit sanitization or filtering of the code content is described before processing.
- [SAFE]: The skill uses the
allowed-toolsconfiguration to limit the execution environment to a minimal set of necessary git commands, adhering to the principle of least privilege.
Audit Metadata