add-key-point-overlays

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external MCP server at https://connect.clueso.io/mcp. This resource belongs to the skill's author and is used to provide the necessary video editing tools.
  • [COMMAND_EXECUTION]: The documentation provides a setup command for Claude Code (claude mcp add --transport http Clueso https://connect.clueso.io/mcp). While this command modifies the agent's environment, it is a standard procedure for adding MCP connectors and points to a verified vendor domain.
  • [PROMPT_INJECTION]: The skill processes video narration transcripts and rendered frames as inputs. This constitutes an indirect prompt injection surface where untrusted data from a video project could contain malicious instructions.
  • Ingestion points: Video narration transcript and rendered frames (SKILL.md).
  • Boundary markers: No specific delimiters or warnings are used to isolate transcript content from agent instructions.
  • Capability inventory: The skill utilizes video editing, overlay placement, and project export tools via the clueso-mcp connector.
  • Sanitization: The instructions do not describe any filtering or sanitization of the input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — add-key-point-overlays