servicem8
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process data from ServiceM8, including job details, emails, and SMS messages. This external content could contain hidden instructions meant to manipulate the agent's behavior.
- Ingestion points: Data retrieved from ServiceM8 endpoints via
membrane action runandmembrane request(SKILL.md). - Boundary markers: No specific delimiters or instruction-ignore warnings are defined for the retrieved content.
- Capability inventory: The skill has the ability to execute shell commands, perform network operations, and write data back to ServiceM8.
- Sanitization: No explicit data sanitization or validation steps are documented for the external inputs.
- [EXTERNAL_DOWNLOADS]: The instructions include the installation of the
@membranehq/clipackage vianpm. This is the official command-line tool for the platform, provided by the vendor to facilitate the integration. - [COMMAND_EXECUTION]: The skill uses shell commands to log in to the Membrane platform and interact with the ServiceM8 API. The
membrane logincommand securely handles authentication by using a browser-based flow or an authorization code, avoiding the need for hardcoded API keys.
Audit Metadata