grammarly
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the NPM registry. This is a vendor-owned CLI tool required for the skill to operate. - [COMMAND_EXECUTION]: The skill executes multiple shell commands using the
membraneCLI to perform authentication (login), search for connectors, manage connections, and execute API actions. These are necessary for the integration's core functionality. - [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from Grammarly, such as writing suggestions and document content, which creates a surface for indirect prompt injection.
- Ingestion points: Document content and suggestions retrieved via
membrane action runormembrane request(SKILL.md). - Boundary markers: None identified in the skill instructions.
- Capability inventory: Shell command execution and network operations through the
membraneCLI (SKILL.md). - Sanitization: No sanitization or filtering of the retrieved Grammarly data is specified.
Audit Metadata