review-dependencies

Warn

Audited by Snyk on Apr 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly requires using "WebSearch" to compare package versions (see Step 2 notes for Swift PM and cargo and Step 3 fallback), which directs the agent to fetch and interpret public web content (package registries, release pages, etc.) that is untrusted and can influence versioning decisions and next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 5, 2026, 03:57 AM
Issues
1