script-to-voiceover
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides specific setup instructions for the user to execute a configuration command (
claude mcp add --transport http Clueso https://connect.clueso.io/mcp). This is presented as a manual, transparent step for the user to connect the required service rather than an automated execution. - [EXTERNAL_DOWNLOADS]: The instructions direct the user to connect to an external MCP server endpoint and view documentation on the vendor's domain (
clueso.io). These references are necessary for the skill's operation and originate from the skill's identified author. - [PROMPT_INJECTION]: The skill is designed to process untrusted user-provided scripts for narration. It currently lacks explicit boundary markers to isolate the script content from instructions, though the risk is minimized by the nature of the downstream audio generation task.
- Ingestion points: User-provided plain-text script as defined in the 'Inputs' section.
- Boundary markers: Absent; the workflow does not instruct the agent to use delimiters when handling the script.
- Capability inventory: The skill utilizes workspace management, project creation, narration generation, and export tools via the Clueso MCP.
- Sanitization: No explicit sanitization or filtering of the script content is performed before processing.
Audit Metadata