shorten-to-length

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the user to execute a command to install a Model Context Protocol (MCP) connector.
  • Evidence: claude mcp add --transport http Clueso https://connect.clueso.io/mcp in SKILL.md.
  • Context: This is a documented setup step to enable the skill's core functionality. The instruction explicitly states it should be run with the user's confirmation.
  • [EXTERNAL_DOWNLOADS]: The skill references an external URL for its required MCP server.
  • Evidence: https://connect.clueso.io/mcp in SKILL.md.
  • Context: The resource belongs to the vendor's official domain (clueso.io) and is essential for the video editing operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external video project data and user-provided instructions, which represents a standard attack surface for indirect prompt injection.
  • Ingestion points: Processes existing Clueso project data and raw recordings provided by the user in the "Inputs" section of SKILL.md.
  • Boundary markers: No specific boundary markers are defined for the ingested data.
  • Capability inventory: Uses Clueso MCP tools for video triage, narration regeneration, and project export as described in the "Workflow" section.
  • Sanitization: The skill mitigates risks by requiring explicit user sign-off on editorial plans and review links before final export.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — shorten-to-length