intercom
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the NPM registry to interact with the Membrane platform. - [COMMAND_EXECUTION]: The skill utilizes the
membraneCLI to authenticate, manage connections, and execute actions or proxy requests against the Intercom API. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from Intercom sources like conversations, messages, and user profiles, which serves as a vector for untrusted content ingestion.
- Ingestion points: Intercom users, contacts, messages, and conversations processed via the CLI tools.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions embedded in the Intercom data.
- Capability inventory: The skill can execute CLI commands and perform network requests via the Membrane proxy system.
- Sanitization: The documentation does not specify any sanitization or validation processes for the data retrieved from external Intercom endpoints.
Audit Metadata