exp-test-maintainability
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no instructions for high-risk operations such as network access, credential handling, or command execution. The workflow is restricted to static analysis of code.
- [INDIRECT_PROMPT_INJECTION]: The skill has a potential surface for indirect injection as it processes untrusted test and production code. 1. Ingestion points: Reads test files and project directories provided by the user (SKILL.md, Workflow Step 1). 2. Boundary markers: None identified in the prompt instructions. 3. Capability inventory: The skill is limited to analysis only; it contains no file-write, network, or subprocess execution capabilities (SKILL.md, Metadata/Workflow). 4. Sanitization: None identified.
Audit Metadata