carbone
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@membranehq/clipackage from the official NPM registry to facilitate communication with the Membrane platform. - [COMMAND_EXECUTION]: The skill makes extensive use of the
membraneCLI to perform operations such as authentication, connection management, and running API actions. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from Carbone, creating an attack surface for indirect prompt injection if external data contains malicious instructions.
- Ingestion points: External data is ingested from Carbone templates and reports via
membrane action runandmembrane request(SKILL.md). - Boundary markers: No explicit boundary markers or "ignore instructions" delimiters are implemented for the ingested data.
- Capability inventory: The agent can execute CLI commands, perform network requests, and manage connections.
- Sanitization: The skill does not describe specific sanitization or validation mechanisms for the data retrieved from the Carbone API.
Audit Metadata