statsig

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's setup instructions direct users to configure an MCP server using npx to execute the mcp-remote package, which connects to the official Statsig API endpoint at https://api.statsig.com/v1/mcp.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Statsig console, such as experiment definitions and gate rules, which could potentially contain instructions. Ingestion points: Tools such as Get_List_of_Experiments and Search / Fetch retrieve data from the Statsig API. Boundary markers: None specified. Capability inventory: The skill can create and update Statsig entities via tools like Create_Gate and Update_Experiment_Entirely. Sanitization: Not explicitly mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 11:41 AM