dial-your-context
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's behavior is entirely consistent with its described purpose of helping users tune their Sanity Context MCP server configuration.
- [DATA_EXFILTRATION]: The skill requests a Sanity write token or OAuth access, which is necessary for its 'Path A' workflow to create draft documents. These interactions are directed at official Sanity endpoints (api.sanity.io) and align with the author's identity (sanity-io).
- [PROMPT_INJECTION]: The skill processes external data returned from GROQ queries. It contains an inherent attack surface for indirect prompt injection from the database content, but mitigates this via a strict workflow requiring user verification of every claim and evidence-based analysis.
Audit Metadata