content-digest
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: 1.00). The skill explicitly fetches and ingests open web sources (e.g., "YouTube links", "Article URLs", "Podcast links" via WebFetch as described in the "If user provides a URL" workflow), which are untrusted/third-party user-generated content that the agent is required to read and interpret for its four-stage summarization process, creating a clear risk of indirect prompt injection.
Audit Metadata