respondio
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from Respond.io, a messaging platform that centralizes conversations from channels like WhatsApp and Facebook Messenger. Data ingested from these external sources represents an attack surface where malicious users could embed instructions to influence the agent.
- Ingestion points: Messaging data retrieved via
membrane action runandmembrane requestcommands. - Boundary markers: None identified; the instructions do not specify delimiters to separate untrusted message content from agent instructions.
- Capability inventory: The skill can execute API actions and perform network requests using the Membrane CLI.
- Sanitization: No specific filtering or sanitization of message content is mentioned in the integration instructions.
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation and use of the
@membranehq/clipackage from the NPM registry. This tool is provided by the vendor to facilitate authentication and API interaction. - [COMMAND_EXECUTION]: The skill relies on executing shell commands via the
membraneCLI to manage connections, discover actions, and perform API requests.
Audit Metadata