split-into-series
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides guidance on connecting to the Clueso service via the Model Context Protocol (MCP). For Claude Code users, the agent is instructed to offer to run the setup command
claude mcp add --transport http Clueso https://connect.clueso.io/mcp. This command interacts with the vendor's official infrastructure and is a standard configuration step for using the skill's required tools. - [PROMPT_INJECTION]: The workflow involves reading video transcripts to identify logical split points (Step 2). This creates a surface for indirect prompt injection, as the agent is processing untrusted data from the video transcript. However, the scope of the skill is strictly limited to video project organization and editing within the Clueso ecosystem.
- Ingestion points: Video transcripts analyzed during the segmentation proposal step in SKILL.md.
- Boundary markers: Not explicitly specified in the instructions.
- Capability inventory: Video project creation, narration editing, and clip manipulation via the Clueso MCP toolset.
- Sanitization: No specific filtering or sanitization of transcript content is mentioned.
Audit Metadata