nylas
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands through the 'membrane' CLI to perform operations such as searching for connectors, establishing connections, and executing API actions.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the '@membranehq/cli' package from the public NPM registry and uses npx to fetch and execute the latest version of the CLI tool.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks common in communication integrations where untrusted data from external sources is processed.
- Ingestion points: Data retrieved from the Nylas API via 'membrane action run' and 'membrane request' (SKILL.md).
- Boundary markers: None present; the instructions do not include delimiters or specific guidance for the agent to ignore instructions embedded in the Nylas data.
- Capability inventory: Shell command execution via the Membrane CLI, including the ability to run arbitrary actions and network requests (SKILL.md).
- Sanitization: No explicit content sanitization or validation of the external API responses is provided in the instructions.
Audit Metadata