vulnerability-research
Warn
Audited by Snyk on Sep 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The vulnerability-research skill guides an AI agent through checking advisory feeds, community sources, bug trackers, and search tools (such as NVD API, GitHub advisories, and searchsploit) where outsider-authored free text is ingested and processed at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata