cx-config
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements secure credential handling by explicitly instructing the agent to accept API keys silently and never repeat, summarize, or confirm the key value back to the user, preventing accidental exposure in the chat history.
- [DATA_EXPOSURE]: The skill manages sensitive configuration in
<plugin-root>/mcp.json. This is the intended behavior for a setup and troubleshooting utility, and it does not involve unauthorized file access or network exfiltration of this data. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files (
mcp.jsonandmcp-settings.md) to determine its execution state. While this represents a data ingestion surface, the risk is minimal as these are local configuration and documentation files within the agent's environment, and the skill's capabilities are restricted to specific configuration updates.
Audit Metadata