video-to-article

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to connect to a remote MCP server at https://connect.clueso.io/mcp. This is a vendor-owned resource necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill provides a command (claude mcp add --transport http Clueso https://connect.clueso.io/mcp) for the agent to configure its environment. The instructions explicitly state this should be done with user confirmation.
  • [PROMPT_INJECTION]: The skill processes untrusted external data (video transcripts) to extract information and generate content. This presents a surface for indirect prompt injection.
  • Ingestion points: Video content and transcripts processed in the Extract the argument structure and Draft the article steps.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the processed transcripts.
  • Capability inventory: The skill uses tools to write to Clueso projects, capture video frames, and generate images.
  • Sanitization: No explicit sanitization or filtering of the transcribed text is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — video-to-article