restructure-help-article

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process existing help articles provided by the user. While this creates a surface for indirect prompt injection (where instructions hidden in the source text might influence the agent), the skill provides specific structural requirements (one heading per step, prerequisites at top) which acts as a form of constraint.
  • Ingestion points: Existing help articles provided via user prompt or file reference.
  • Boundary markers: None explicitly defined.
  • Capability inventory: Accesses Clueso tools via MCP.
  • Sanitization: Not explicitly performed.
  • [COMMAND_EXECUTION]: The skill provides the command claude mcp add --transport http Clueso https://connect.clueso.io/mcp for users of Claude Code. This command connects the agent to the Clueso Model Context Protocol (MCP) server. This is a standard configuration step for using the intended tool and points to the vendor's official domain (clueso.io).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — restructure-help-article