rest-api-expert

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard shell commands (grep, ls, find) to detect the project environment, specifically looking for API frameworks like Express, Fastify, and NestJS, as well as OpenAPI/Swagger specifications.
  • [DATA_EXPOSURE]: The skill reads local file system metadata and contents (e.g., package.json, source files) to identify the project's structure and existing API routes. No sensitive data is targeted for exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local data from the user's project files during environment detection.
  • Ingestion points: Reads package.json and various source files (*.ts, *.js, *.yaml, *.json) via shell commands.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used for the discovered data.
  • Capability inventory: The skill has no capabilities to perform network operations, file writes, or sensitive subprocess executions based on the ingested data.
  • Sanitization: No explicit sanitization of the file contents is performed as the data is used for structural discovery only.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:08 AM
Security Audit — agent-trust-hub — rest-api-expert