plan-skill

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill's workflow explicitly permits "do lightweight web research (read-only) and summarize key points," which requires fetching and reading public web content (open third-party sites) as part of its analysis, exposing the agent to untrusted user-generated or public webpages.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:53 AM