writing-api-tests
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill promotes secure credential management by instructing the agent to retrieve accounts and keys from approved configurations rather than hardcoding them in scripts or reports.\n- [SAFE]: External documentation links are restricted to well-known and trusted organizations, specifically OWASP and Amazon (AWS), ensuring the testing methodologies are based on secure industry standards.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which constitutes a potential injection surface.\n
- Ingestion points: Ingests requirements, API contracts, and existing test case documentation (SKILL.md).\n
- Boundary markers: None explicitly defined in the instructions to separate untrusted content.\n
- Capability inventory: Includes the ability to write test files and execute shell commands/test runners.\n
- Sanitization: Not explicitly detailed, though the workflow emphasizes verifying outputs against independent, pre-defined rules.
Audit Metadata