markdown-fetch
Warn
Audited by Snyk on Mar 8, 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 explicitly fetches and converts arbitrary public webpages provided as URLs (see SKILL.md "Triggering" and the scripts/fetch.sh which POSTs the user-supplied URL to https://markdown.new/), so untrusted, user-generated third‑party content is ingested and intended to be read/used by the agent, enabling indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The fetch.sh script makes a runtime POST to the external service "https://markdown.new/" which returns arbitrary Markdown-converted webpage content that the skill injects into the agent's output/context for summarization/analysis, meaning remote content can directly control prompts at runtime.
Audit Metadata