research-add-items
Warn
Audited by Snyk on Jun 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill ingests outsider-authored free text when it optionally launches a web-search subagent (public web content fetched at runtime) and then merges the subagent’s suggestions into the LLM-visible candidate list for user confirmation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata