dial-your-context

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a configuration workflow for Sanity.io services. It handles user-provided identifiers and tokens to perform legitimate data analysis and write configuration updates to the user's Sanity dataset.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes data from external Sanity datasets to generate configuration instructions.
  • Ingestion points: The agent retrieves the database schema and GROQ query results in SKILL.md (Step 2 and Step 4).
  • Boundary markers: No specific delimiters or instructions are used to separate ingested data from the agent's control logic.
  • Capability inventory: The agent uses the Sanity MCP tool to perform read/write operations on the dataset.
  • Sanitization: The skill does not specify any validation or sanitization routines for the content returned by the GROQ queries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 06:12 PM