web-researcher
Warn
Audited by Snyk on Jul 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). This skill is a “web research” workflow that (by its instructions) would fetch and quote/paraphrase content from public web pages (outsider-authored free text) into the agent’s notes/synthesis, which are then fed into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata