investigation-mode

Warn

Audited by Snyk on Feb 15, 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 "Deep Research" step instructs dispatching a subagent to "execute web fetch for official docs, RFCs, known issues and return a cited Context Package," which requires retrieving and interpreting content from public third-party websites (including user-generated "known issues") during runtime.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:10 PM