pabbly
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Downloads the Membrane CLI package (@membranehq/cli) from the official npm registry to facilitate communication with the platform.
- [COMMAND_EXECUTION]: Utilizes the membrane command-line interface to perform authentication (membrane login), manage application connections, and run Pabbly actions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Pabbly APIs and actions, which represents a potential surface for instructions embedded in third-party data.
- Ingestion points: Responses from membrane action run and membrane request (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded content are provided for the data processed.
- Capability inventory: The skill can execute CLI commands and perform network operations via the Membrane proxy (SKILL.md).
- Sanitization: No explicit sanitization of Pabbly data is described before the agent processes it.
Audit Metadata