read-url-markdown

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes system processes using spawn to launch browser executables (Chrome, Edge, or Chromium) for page rendering. This is documented behavior required for its primary function.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from arbitrary user-provided URLs and converts it into markdown which is then presented to the agent.
  • Ingestion points: The captureUrl function in scripts/main.ts fetches content from external URLs.
  • Boundary markers: The output format uses YAML frontmatter delimiters (---), but does not include explicit warnings to the agent to ignore instructions embedded within the scraped content.
  • Capability inventory: The skill has capabilities to execute shell commands (spawning the browser) and write files to the local system (scripts/main.ts).
  • Sanitization: The skill removes scripts, styles, and other executable tags from the HTML before conversion, but the semantic text content remains unvalidated.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 03:50 PM
Security Audit — agent-trust-hub — read-url-markdown