one-api-routes
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents how to process untrusted external data through server-side API endpoints.
- Ingestion points: The documentation in
SKILL.mdprovides examples for extracting data from HTTP requests usingrequest.json(),request.formData(), andrequest.text(). - Boundary markers: The provided code templates do not include specific delimiters or instructions for the agent to treat this external content as untrusted.
- Capability inventory: The templates demonstrate the ability to perform database operations (
db.users.create(body),db.users.update(params.id, body)) and external network requests (fetch('https://upstream.api...')). - Sanitization: No input validation, escaping, or sanitization logic is present in the examples, allowing raw external data to be passed directly to database and network operations.
Audit Metadata