full-page-translate

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from external URLs, creating an attack surface for indirect prompt injection.\n
  • Ingestion points: Markdown content is fetched from external URLs via r.jina.ai as described in SKILL.md.\n
  • Boundary markers: No delimiters or 'ignore' instructions are provided in SKILL.md to separate content from instructions.\n
  • Capability inventory: The skill only performs text processing and has no access to dangerous tools like shell execution or file system writes.\n
  • Sanitization: The skill does not perform any sanitization or validation of the fetched markdown.\n- [EXTERNAL_DOWNLOADS]: The skill fetches markdown from r.jina.ai, which is a well-known and reputable service for converting web content for AI analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — full-page-translate