smooch
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
membraneCLI tool to perform operations such as logging in, managing connectors, and executing actions against the Smooch API. - [EXTERNAL_DOWNLOADS]: The skill directs the installation of the
@membranehq/clipackage from the npm registry. This is the official vendor-provided tool required for the skill's functionality. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection when handling data from Smooch messaging channels.
- Ingestion points: External data is brought into the agent context through results from
membrane action runandmembrane requestcommands. - Boundary markers: No specific delimiters or boundary instructions are defined to separate untrusted API data from agent instructions.
- Capability inventory: The skill uses the
membraneCLI which provides capabilities for network requests and action execution. - Sanitization: There is no evidence of content sanitization or validation of the retrieved API content before it is processed by the agent.
Audit Metadata