api-testing
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Instructions guide the installation and execution of standard API testing CLI tools, including @usebruno/cli, newman, and k6, for both local verification and CI/CD pipeline integration.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and package installations from well-known services and trusted organizations such as Postman, Bruno, and Grafana (k6).
- [PROMPT_INJECTION]: The skill ingests and processes untrusted data from external API responses, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: API response bodies are processed in SKILL.md through scripts using res.getBody(), pm.response.json(), and createRes.json().
- Boundary markers: The provided examples do not include explicit boundary markers or warnings to the agent to ignore instructions embedded in API responses.
- Capability inventory: The skill allows the agent to perform network requests and modify environment variables based on response data.
- Sanitization: There is no logic shown for sanitizing or validating external response content before it is extracted and used in subsequent agent steps.
Audit Metadata