research

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: 0.90). The skill's Phase 2 "Search Strategy" explicitly instructs the agent to run gemini or a WebSearch tool to fetch/search the open web and to use the docs-seeker to read GitHub repository URLs, so it will ingest and interpret untrusted, user-generated third-party content from public websites and repos.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:19 AM