wiki-ingest
Warn
Audited by Snyk on May 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts URLs ("Accept the source" — use the
browseskill to fetch it) and then requires the agent to read and interpret that fetched web content to generate summaries and update wiki pages, so arbitrary third‑party web pages could indirectly inject instructions affecting agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata