openapi-endpoints
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The agent is instructed to run
npx tsx scripts/generate-openapi.ts. This involves executing a local TypeScript script to generate API documentation. - [PROMPT_INJECTION]: An indirect prompt injection surface is present. Ingestion points: The agent reads
src/app/api/<path>/route.ts,src/app/api/<path>/schema.ts, and supplement files. Boundary markers: The agent prompt templates do not include instructions to ignore instructions embedded within these files. Capability inventory: The agent has capabilities for file system modification and script execution. Sanitization: There is no specified validation or sanitization of the content read from the source files.
Audit Metadata