search-specialist

Warn

Audited by Snyk on Feb 27, 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). This skill's SKILL.md (see "WebFetch Deep Dive") explicitly directs the agent to "Extract full content from promising results" and "Follow citation trails and references," which requires fetching and ingesting untrusted public web content that can influence subsequent decisions and tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 08:55 AM