one-recording-full-launch-kit

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes external content from feature recordings to generate marketing deliverables like scripts and changelog blurbs.
  • Ingestion points: Transcripts and structure analysis of feature recordings (SKILL.md, Workflow step 1).
  • Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore instructions that might be embedded in the recording transcripts.
  • Capability inventory: The skill utilizes the clueso-mcp to create video projects, generate narration, and modify workspace articles.
  • Sanitization: Absent; no explicit escaping or filtering of the transcribed content is defined before processing.
  • [COMMAND_EXECUTION]: The skill provides platform-specific commands for the agent to offer to the user to configure the Clueso MCP connection.
  • Evidence: claude mcp add --transport http Clueso https://connect.clueso.io/mcp (SKILL.md, "Before you start").
  • Context: These commands are documented for environment setup and are intended to be executed with user confirmation.
  • [EXTERNAL_DOWNLOADS]: The skill references the vendor's MCP server and setup documentation.
  • Evidence: Fetches configuration and setup guides from https://connect.clueso.io/mcp and https://help.clueso.io/mcp-setup.
  • Context: These resources originate from the skill's author domain (clueso.io) and are required for the intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 06:28 AM