web-to-markdown

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the web2md CLI tool to perform browser automation and conversion. It also uses standard shell commands like mkdir, ls, and wc, and provides installation steps involving npm.
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch and process content from external URLs. Additionally, the installation process uses npm install, which retrieves packages from the public npm registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted web content which is then converted to Markdown and provided to the agent. This represents an attack surface where a malicious website could attempt to influence the agent via embedded instructions.
  • Ingestion points: External content is retrieved via the url parameter passed to web2md (SKILL.md).
  • Boundary markers: The skill does not provide instructions to the agent to treat the converted content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The agent has capabilities to execute shell commands, perform network requests (via the browser tool), and write to the local file system.
  • Sanitization: While the tool uses Readability and Turndown to clean HTML structure, it does not sanitize the resulting text for potential malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 04:05 PM
Security Audit — agent-trust-hub — web-to-markdown