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
web2mdCLI tool to perform browser automation and conversion. It also uses standard shell commands likemkdir,ls, andwc, and provides installation steps involvingnpm. - [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
urlparameter passed toweb2md(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