skills/clueso-ai/skills/swap-voice/Gen Agent Trust Hub

swap-voice

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes video transcripts to analyze content and suggest voice matches, creating a surface for indirect prompt injection.
  • Ingestion points: Video transcripts are read in Workflow Step 2 to determine the video's context.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic.
  • Capability inventory: The skill utilizes the clueso-mcp toolset to regenerate narration and retime video clips.
  • Sanitization: There is no evidence of sanitization or filtering of the transcript content before analysis.
  • [COMMAND_EXECUTION]: The skill instructs users on how to manually configure tool connections using CLI commands such as claude mcp add.
  • [EXTERNAL_DOWNLOADS]: The documentation references external setup guides and connection endpoints at clueso.io subdomains, which are associated with the skill's author.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — swap-voice