interhuman-post-processing

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of data from an external API (api.interhuman.ai) and instructs the agent to return the raw JSON response without modification. This represents a surface for indirect prompt injection, though it is the primary intended function for an API wrapper.
  • Ingestion points: API response content from the /v1/upload/analyze endpoint (SKILL.md).
  • Boundary markers: Absent; instructions require providing the exact JSON response to the user.
  • Capability inventory: Network requests via curl, requests (Python), and node-fetch (Node.js) are documented for API interaction (SKILL.md).
  • Sanitization: None; the instructions explicitly forbid any filtering or transformation of the API response.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 02:17 PM