rocketreach
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
@membranehq/cliutility from the NPM registry to manage RocketReach interactions. - [COMMAND_EXECUTION]: Instructions include the use of terminal commands to authenticate the user and execute API actions through the Membrane framework.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a conduit for data from RocketReach, which involves processing externally sourced professional and company information. This constitutes a standard injection surface common to data retrieval skills.
- Ingestion points: Data retrieved from RocketReach endpoints via
membrane action runormembrane request(SKILL.md). - Boundary markers: The skill does not define specific prompt delimiters for external content.
- Capability inventory: Network requests to RocketReach API and local CLI execution for configuration management.
- Sanitization: Standard handling by the underlying Membrane platform is assumed, though not explicitly detailed in the skill markdown.
Audit Metadata