wiki-research

Warn

Audited by Snyk on May 18, 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.md explicitly instructs the agent to run WebSearch queries and use WebFetch (or "defuddle ") to retrieve top results in Round 1 and then extract claims/concepts/contradictions from those fetched public web pages to drive synthesis and wiki edits, so untrusted third‑party content from open websites can materially influence the agent's decisions and actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 18, 2026, 07:37 PM
Issues
1