evaluating-threat-intelligence-platforms

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's agent code (scripts/agent.py — specifically test_misp_api and test_opencti_api) and the API examples (references/api-reference.md) explicitly fetch and parse JSON/STIX/TAXII data from user-supplied MISP/OpenCTI/TAXII URLs, meaning untrusted third‑party content is ingested and can influence the agent's evaluation and actions.