api-test-suite-builder
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to scan and read user-provided source code files to identify API routes and business logic. This ingestion of untrusted data creates a surface for indirect prompt injection where malicious instructions embedded in the scanned files could attempt to influence the agent's behavior.
- Ingestion points: Source files scanned by
findandgrepcommands defined inSKILL.md. - Boundary markers: None identified to separate scanned content from agent instructions.
- Capability inventory: The agent using this skill typically has capabilities for terminal command execution and file manipulation to generate the test suites.
- Sanitization: No sanitization or validation of the ingested source code is performed before processing.
Audit Metadata