video-to-job-aid
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill guides the user to configure a remote Model Context Protocol (MCP) server from the vendor's official domain at
https://connect.clueso.io/mcp. This is a standard integration for Clueso-related skills. - [COMMAND_EXECUTION]: Provides shell commands (e.g.,
claude mcp add --transport http Clueso https://connect.clueso.io/mcp) for the user to manually execute to set up the necessary environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data derived from training video transcriptions and visual analysis, creating an attack surface for indirect prompt injection.
- Ingestion points: Video content analysis and transcription in Step 2 of the workflow.
- Boundary markers: None explicitly defined to separate processed video data from agent instructions.
- Capability inventory: The skill has the ability to author articles and write data to Clueso projects via tool calls.
- Sanitization: The workflow includes a condensation step (Step 4) which requires the agent to rewrite content into a specific imperative format, providing a layer of natural language filtering.
Audit Metadata