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
npxto execute themcp-remotepackage, which connects to the official Statsig API endpoint athttps://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_ExperimentsandSearch / Fetchretrieve data from the Statsig API. Boundary markers: None specified. Capability inventory: The skill can create and update Statsig entities via tools likeCreate_GateandUpdate_Experiment_Entirely. Sanitization: Not explicitly mentioned.
Audit Metadata