security-analyzer

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

• Third-party content exposure detected (high risk: 0.90). The skill's fetch_vulns.py explicitly queries the public OSV.dev API and the SKILL.md/README instructs supplementing with WebSearch for CISA KEV, NVD, and GitHub Advisories, so the agent ingests open/public third‑party web data that directly influences risk scoring and remediation actions.