wiki-research
Warn
Audited by Snyk on May 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to run WebSearch queries and use WebFetch/defuddle to retrieve and extract content from top web results (Round 1 — Broad Survey step 3), which are open/public third‑party pages whose untrusted/user‑generated content the agent must read and synthesize into wiki pages, allowing embedded instructions to influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata