lov-academic-translator

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions specify commands for the user to install and decrypt content using vendor-managed tools.
  • Evidence: SKILL.md includes npx lovstudio skills add academic-translator and uvx lovstudio-skill-helper decrypt academic-translator.
  • Context: These tools are provided by the author lovstudio for managing paid skills.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and manages encrypted code files using a manifest, which are decrypted at runtime.
  • Evidence: MANIFEST.enc.json defines AES-256-GCM encryption for all script files.
  • [PROMPT_INJECTION]: The skill processes user-supplied PDFs for translation, which is a surface for indirect prompt injection attacks.
  • Ingestion points: Academic PDFs, technical journals, and technical articles processed via scripts/translate_paper_pdf.py.
  • Boundary markers: Unverifiable due to source code encryption.
  • Capability inventory: PDF processing and translation logic in scripts/translate_paper_pdf.py.
  • Sanitization: Unverifiable due to source code encryption.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:55 AM
Security Audit — agent-trust-hub — lov-academic-translator