study

Warn

Audited by Snyk on Aug 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). Source: the skill’s runtime “Identification & Grounding” Step 1 reads either a user-passed file/snippet via view_file or searches official documentation/IETF RFCs via search_web, meaning outsider-authored text can be ingested from user-provided file paths/snippets and from whatever pages search_web fetches.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 22, 2026, 12:22 AM
Issues
1