markdown-url
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill routes web browsing through an external proxy service (markdown.new) to retrieve content in markdown format. This exposes the agent to indirect prompt injection, where malicious instructions embedded in target web pages could be processed and potentially obeyed by the agent.
- Ingestion points: External website content retrieved via the markdown.new proxy into the agent's context.
- Boundary markers: Absent. The skill does not provide instructions to the agent to treat the retrieved content as untrusted or to ignore embedded commands.
- Capability inventory: The agent uses network operations to visit URLs and processes the resulting text for summarization and note-taking.
- Sanitization: No validation or sanitization of the retrieved content is mentioned.
- [COMMAND_EXECUTION]: The documentation references the execution of a local Node.js script (node skills/markdown-url/scripts/markdown-url.js) used as a CLI helper to transform URLs. This indicates the skill includes and executes local script files.
Audit Metadata