rebrand-video-library

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted external data in the form of video transcripts and rendered frames to identify branding artifacts.
  • Ingestion points: Video transcripts and rendered frames are ingested for auditing in the 'Look before you touch' workflow (SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to ignore or escape instructions that may be embedded within the video transcripts.
  • Capability inventory: The skill possesses the capability to modify video projects, recolor elements, and replace assets through the 'clueso-mcp' tools.
  • Sanitization: No sanitization or validation logic is specified for the transcript content before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill requires the agent to connect to an external Model Context Protocol (MCP) server at https://connect.clueso.io/mcp. This server is part of the vendor's infrastructure (clueso.io) and is necessary to provide the video editing tools described in the workflow.
  • [COMMAND_EXECUTION]: The instructions include a configuration command for Claude Code users (claude mcp add --transport http Clueso https://connect.clueso.io/mcp). This command is used to register the vendor's remote toolset with the agent environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — rebrand-video-library