validating-api-responses
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted external data.
- Ingestion points: The skill instructions (
SKILL.md) direct the agent to read OpenAPI specifications from the local filesystem, and implementation examples (references/examples.md) demonstrate fetching API responses from local or remote endpoints. - Boundary markers: There are no explicit delimiters or instructions to the agent to disregard potentially malicious content within the ingested data.
- Capability inventory: The agent has access to
Bash,Write,Edit, andReadtools across all provided scripts and instructions, which could be misused if malicious instructions are processed. - Sanitization: The provided examples do not include sanitization, validation of data source integrity, or filtering of the ingested content before it enters the agent's context.
Audit Metadata