backend-test-additions
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external codebase content such as target modules, existing test files, and repository configurations to generate new test suites. This introduces a surface for indirect prompt injection where malicious instructions embedded in the analyzed code could influence the agent's behavior during test generation.
- Ingestion points: Target module/endpoint/job, existing test stack/conventions, and REPO_PROFILE.json.
- Boundary markers: The workflow does not specify the use of delimiters or 'ignore' instructions for external content.
- Capability inventory: The skill has file-write permissions ('mode: write') and the ability to execute repository test commands.
- Sanitization: The instructions do not include steps for sanitizing or validating external code inputs.
Audit Metadata