skills-creator
Warn
Audited by Snyk on Mar 1, 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 reference docs explicitly include a conditional workflow that says "Is input a URL?
- Yes: Use
scripts/fetch_remote.py" (references/REFERENCE.md) and the spec examples mention requiring internet access, which shows the agent may fetch and ingest arbitrary user-provided/public URLs and read their contents as part of its workflow, exposing it to untrusted third‑party content that could inject instructions.
Audit Metadata