learn-this
Warn
Audited by Snyk on Mar 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly fetches and ingests arbitrary public URLs (Step 2: "Extract Content" — using youtube-transcript/yt-dlp for YouTube, trafilatura/curl for articles, and curl/pdftotext for PDFs) and then reads/interprets that untrusted third‑party content to automatically create action plans, so web-hosted/user-generated content can directly influence agent decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill fetches arbitrary user-supplied URLs at runtime (e.g., curl -s "$URL", curl -L -o "$PDF_FILENAME" "$URL", and yt-dlp "$URL") and then injects that fetched content into the action-planning workflow to generate prompts/instructions, so remote content can directly control the agent's behavior.
Audit Metadata