tighten-narration

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions define a legitimate workflow for video editing using the Clueso toolset.
  • [EXTERNAL_DOWNLOADS]: The skill connects to official vendor endpoints (connect.clueso.io) which is standard for its described purpose.
  • [COMMAND_EXECUTION]: The instructions include usage of the claude mcp add command to configure the local environment with the Clueso MCP server.
  • [PROMPT_INJECTION]: The workflow involves processing user-provided transcripts, creating a surface for indirect prompt injection. This risk is inherent to the script-editing function and is not accompanied by any malicious indicators.
  • Ingestion points: The transcript is read in workflow step 2.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflow.
  • Capability inventory: The skill utilizes tools for narration regeneration, visual alignment, and video export.
  • Sanitization: No sanitization or validation of the transcript content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — tighten-narration