proofpoint
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to download and install the official Membrane CLI via npm (
@membranehq/cli@latest) to facilitate interaction with the platform. - [COMMAND_EXECUTION]: The skill uses the
membraneCLI to perform authentication, connection management, and to execute actions against the Proofpoint API. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Proofpoint, including email messages, attachments, and threat insights, which could theoretically contain malicious instructions.
- Ingestion points: Data retrieved from Proofpoint API endpoints (e.g., Email Message, Threat Insight, URL).
- Boundary markers: None explicitly defined in the instructions to separate data from instructions.
- Capability inventory: Shell command execution via the
membraneCLI for running actions and proxying API requests. - Sanitization: No explicit sanitization or filtering of external content is described in the skill body.
Audit Metadata