trengo
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the Membrane CLI (
@membranehq/cli) from the NPM registry. This is a standard requirement for interacting with the vendor's platform. - [COMMAND_EXECUTION]: Uses the
membraneCLI to perform various integration tasks such as authentication, searching for connectors, and running actions against the Trengo API. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted data from Trengo (e.g., messages from WhatsApp, email, or social media).
- Ingestion points: External data is retrieved via
membrane action runandmembrane requestcommands in SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or warnings for the agent when processing retrieved customer message content.
- Capability inventory: The skill allows the agent to read and write data to Trengo and execute CLI commands as documented in SKILL.md.
- Sanitization: There is no mention of sanitizing or escaping the data retrieved from Trengo before it is processed by the agent.
Audit Metadata