summarize
Warn
Audited by Snyk on Mar 3, 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.md explicitly states the CLI fetches and summarizes arbitrary public URLs and third‑party content (web pages, PDFs, YouTube — e.g., the example
summarize "https://example.com"), so the agent ingests untrusted user/website content as part of its workflow which could carry indirect prompt injections.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The summarize CLI fetches and ingests arbitrary remote URLs at runtime (e.g., https://example.com and https://youtu.be/dQw4w9WgXcQ), so remotely served content can be injected into model prompts and therefore directly control instructions.
Audit Metadata