workflow

Warn

Audited by Snyk on Mar 25, 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 review flow explicitly instructs using web search when available ("IF WebSearch/web capabilities available: Search in parallel..." in references/actions/review.md) and to synthesize those public web results into a language-specific overlay that influences production-mode reviews, which means it can fetch and act on untrusted third-party web content during normal workflow.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 25, 2026, 04:39 PM
Issues
1