annotate-article-screenshots

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill mentions the command claude mcp add --transport http Clueso https://connect.clueso.io/mcp. This is a documented, standard configuration command for adding Model Context Protocol (MCP) servers to the Claude Code environment. It targets a well-known service domain (clueso.io) associated with the skill's stated purpose and author (clueso-ai).
  • [EXTERNAL_DOWNLOADS]: The skill references several URLs under help.clueso.io and connect.clueso.io. These are official documentation and connection endpoints for the Clueso platform, which is the primary tool this skill is designed to interact with. These references are used to provide setup guidance to the user.
  • [DATA_EXFILTRATION]: The skill actually includes explicit instructions to prevent data exposure by instructing the agent to 'Blur what shouldn't ship,' specifically naming emails, names, tokens, and internal URLs as items to be obscured.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — annotate-article-screenshots