pushbots
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
@membranehq/clipackage globally via npm. This is the official command-line interface for the Membrane platform and is required for the skill's functionality. - [COMMAND_EXECUTION]: The instructions involve running various
membraneCLI commands to authenticate, connect to PushBots, and execute API actions. These commands are the intended method of interaction for this integration. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it retrieves and processes data from external PushBots API endpoints.
- Ingestion points: Data enters the agent context through the output of
membrane action runandmembrane requestcommands. - Boundary markers: No specific delimiters are used in the provided examples to wrap external data.
- Capability inventory: The skill uses the
membraneCLI which has the capability to perform network requests and execute predefined actions. - Sanitization: There are no explicit instructions for sanitizing the output from the PushBots API before processing.
Audit Metadata