api-test-suite-builder

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands like find, grep, and sed to automate the discovery of API routes within a local codebase. These commands are scoped to specific directories (e.g., ./app/api, ./src) and are used for static analysis purposes.
  • [PROMPT_INJECTION]: The skill processes untrusted local source code files to extract route definitions, creating a surface for indirect prompt injection.
  • Ingestion points: Scanning logic in SKILL.md that reads route definitions from framework-specific directories using shell patterns.
  • Boundary markers: None identified; extracted route strings and HTTP methods are directly used to generate test scaffolding.
  • Capability inventory: The skill performs local file system reads and generates executable test code in Node.js and Python.
  • Sanitization: No explicit sanitization or validation of extracted route metadata is performed before interpolation into generated test files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 07:21 AM
Security Audit — agent-trust-hub — api-test-suite-builder