rest-api-doc
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it processes untrusted external data (route definitions, controller code, and prose) to generate its output.
- Ingestion points: The workflow in
SKILL.mdexplicitly accepts raw code, curl examples, and plain prose descriptions as input. - Boundary markers: There are no explicit markers or instructions provided to the agent to distinguish between documentation instructions and potentially malicious content embedded within the source code comments or strings being analyzed.
- Capability inventory: The skill is authorized to write files to the
/mnt/user-data/outputs/directory and use thepresent_filestool to display them to the user. - Sanitization: The instructions do not specify any sanitization or validation steps for the input data before it is interpolated into the markdown or OpenAPI templates.
Audit Metadata