threat-intelligence-feed

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to fetch and ingest "External feeds (via WebSearch)" such as NIST NVD, GitHub Security Advisories, and OWASP updates (see Step 1 and Tools: WebSearch), which are public third‑party sources the agent reads and uses to drive prioritization and patching decisions, so their content could materially influence actions and enable indirect prompt injection.