article-processing
Warn
Audited by Snyk on Jun 20, 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). The skill’s runtime workflow includes “Extract the source article in the browser” (step 4) from user-supplied web article URLs, which are outsider-authored public web pages whose readable body text is ingested into the agent’s LLM context via browser extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata