lov-subtitle-freedom

Warn

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill's functional code is completely obfuscated through AES-256-GCM encryption, as detailed in the MANIFEST.enc.json and evidenced by the binary .enc files (e.g., scripts/subtitle_gloss.py.enc, scripts/ass_styled_subtitle.py.enc). This prevents any static audit of the scripts being executed by the agent.
  • [REMOTE_CODE_EXECUTION]: The skill requires the execution of remote binaries via npx lovstudio and uvx lovstudio-skill-helper. These tools are responsible for adding the skill and decrypting its contents into memory at runtime, creating an unauditable execution chain.
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to fetch components and helper tools from the vendor's infrastructure, which are necessary for the skill to function but remain outside the analyzed package scope.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 24, 2026, 12:55 AM
Security Audit — agent-trust-hub — lov-subtitle-freedom