skill-pipeline

Warn

Audited by Snyk on Feb 16, 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's refinement workflow and references/sources.md explicitly instruct the agent to "check for updates", "fetch and summarize" and load external sources (e.g., GitHub releases, security advisories, blogs, YouTube/community links listed in references/sources.md and the Refinement Process), meaning the agent will ingest untrusted public web/user-generated content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:04 AM