web-markdown-navigator
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted web content which could contain instructions designed to manipulate the agent's behavior.
- Ingestion points:
scripts/fetch-markdown.mjsfetches HTML from external URLs provided as input. - Boundary markers: The skill does not provide the agent with explicit instructions to ignore potentially malicious commands embedded in the converted markdown.
- Capability inventory: The skill performs network requests and file system execution (via the provided scripts) to fetch and process content.
- Sanitization: The script uses @mozilla/readability and turndown to convert HTML to Markdown, which removes executable scripts and tags, but leaves the underlying natural language content which can be used for indirect injection.
Audit Metadata