api-testing
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted documentation (OpenAPI/Swagger) and test schemas which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill ingests OpenAPI/Swagger documents and case schemas as its primary input for testing logic (defined in SKILL.md under Step 1).
- Boundary markers: There are no explicit delimiters or boundary markers used to isolate the untrusted external data from the skill's instructions.
- Capability inventory: The skill possesses capabilities for file system writes (generating reports and scripts), network operations (API sessions and performance tests), and command-line execution (pytest and k6).
- Sanitization: The instructions do not define any sanitization or validation protocols for the content extracted from external documentation.
- [DYNAMIC_EXECUTION]: The skill generates executable Python (pytest) and JavaScript (k6) scripts from templates at runtime and subsequently executes them.
- Evidence: SKILL.md and references/k6-conventions.md describe the dynamic creation of files like 'test_{module}_{interface}.py' and 'load-xxx.js', which are then executed via 'pytest' and 'k6 run' commands.
Audit Metadata