url-to-markdown-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to fetch and convert arbitrary external web content, which constitutes a significant attack surface for indirect prompt injection. Malicious actors could place hidden instructions on web pages designed to hijack the agent's logic when the page is processed.
  • Ingestion points: Content retrieved from user-provided URLs via the POST /api/v1/extract endpoint.
  • Boundary markers: The skill instructions do not specify any markers or delimiters to isolate fetched content from the agent's core instructions.
  • Capability inventory: The fetched content is intended for consumption by the LLM (prompts/RAG); no direct command execution or file system capabilities are present in the skill itself.
  • Sanitization: There is no evidence of content sanitization or instruction-filtering before the data is returned to the agent.
  • [EXTERNAL_DOWNLOADS]: The skill documentation encourages the installation of the vendor's official library to facilitate API interactions.
  • Evidence: Mentions of pip install scavio==0.15.0 and npm install scavio@0.15.0 for Python and Node.js environments respectively.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:23 PM
Security Audit — agent-trust-hub — url-to-markdown-api