clix-skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes data from the clix-mcp-server to generate content for new skill files. This creates a surface where external documentation could influence the generated skill's behavior. (Ingestion: MCP tool outputs; Boundaries: Absent; Capability: File system write; Sanitization: Absent).
  • Dynamic Execution (LOW): The scripts/validate-skill-scaffold.sh script executes embedded Python or Node.js code to validate the structure of newly created skills. While this is a form of dynamic execution, it is limited to local validation logic and does not execute external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:27 PM