1crm
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the '@membranehq/cli' utility from the npm registry, which is a standard resource provided by the vendor to facilitate platform interactions.
- [COMMAND_EXECUTION]: The agent is directed to use the 'membrane' CLI for operational tasks such as login, connection management, and running CRM actions, which are necessary for the skill's intended functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection. 1. Ingestion points: Data retrieved from 1CRM through 'membrane action run' or 'membrane request' (SKILL.md). 2. Boundary markers: None are explicitly defined to isolate external CRM content. 3. Capability inventory: The skill facilitates the execution of CLI commands via the 'membrane' tool (SKILL.md). 4. Sanitization: There are no instructions for sanitizing or escaping the data fetched from the external CRM service.
Audit Metadata