fetch-webpage
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill correctly implements its functionality using a hardcoded list of Markdown proxy providers and native Node.js features without external dependencies.\n- [PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection because it processes untrusted content from external websites.\n
- Ingestion points: Raw webpage content is retrieved via the
fetchWebpagefunction inscripts/fetch.mjs.\n - Boundary markers: Absent. The content is returned as raw Markdown text to the caller.\n
- Capability inventory: The skill is restricted to read operations and does not possess capabilities for file writing, system modification, or command execution.\n
- Sanitization: Absent. Content is processed and returned as plain text.
Audit Metadata