webinar-to-highlight-clips
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes video transcripts and topic breakdowns, which are external data sources that could contain instructions intended to influence the agent's behavior.
- Ingestion points: Spoken audio transcript and topic breakdown as described in the workflow (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or safety prompts to ignore instructions within the transcript data.
- Capability inventory: The skill uses Clueso MCP tools to perform video editing tasks including splitting timelines, duplicating projects, and rendering exports.
- Sanitization: There is no mention of filtering or sanitizing the transcript content before analysis.
- [COMMAND_EXECUTION]: The skill provides instructions for configuring the Clueso Model Context Protocol (MCP) connector, which involves running platform-specific commands.
- Evidence: The skill suggests running
claude mcp add --transport http Clueso https://connect.clueso.io/mcpto integrate Clueso's video editing capabilities. - Context: These commands are intended to establish a connection to the Clueso platform's official infrastructure.
Audit Metadata