add-zoom-emphasis
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to set up the necessary environment by adding a Model Context Protocol (MCP) connector.
- Evidence: Specific commands such as
claude mcp add --transport http Clueso https://connect.clueso.io/mcpare documented for the agent to perform upon user confirmation. - [EXTERNAL_DOWNLOADS]: The skill references external URLs for service connection and documentation.
- Evidence: The skill points to
https://connect.clueso.io/mcpfor tool connection andhttps://help.clueso.io/mcp-setupfor setup guides. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external, potentially untrusted data to perform its primary function.
- Ingestion points: Ingests narration transcripts and rendered video frames to identify emphasis points.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content embedded within the transcript or frames.
- Capability inventory: The skill has the capability to modify project coordinates, timing, and perform video exports via the Clueso toolset.
- Sanitization: There is no mention of sanitization or validation for the content of the transcript or video metadata.
Audit Metadata