grist
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the official Membrane CLI (@membranehq/cli) from the npm registry to interact with the platform. This is a vendor-owned resource used for legitimate platform functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Grist, creating an attack surface for indirect prompt injection. 1. Ingestion points: Data is retrieved from Grist via actions such as
list-records,get-document, andrun-sql-querydocumented in SKILL.md. 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill instructions. 3. Capability inventory: The skill can modify records (create, update, delete) and execute arbitrary API requests via themembrane requestcommand in SKILL.md. 4. Sanitization: There is no mention of sanitization or validation for the content retrieved from external spreadsheets.
Audit Metadata