fullcontact
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Instructions specify installing the
@membranehq/clipackage via NPM to facilitate interaction with the platform. - [COMMAND_EXECUTION]: Uses the
membraneCLI to perform authentication, connection setup, action discovery, and API requests. - [PROMPT_INJECTION]: The skill processes profile enrichment data from the FullContact API which could contain malicious instructions. * Ingestion points: API responses from actions like
enrich-personandenrich-company. * Boundary markers: None specified in the instructions to delimit external data. * Capability inventory: Ability to executemembraneCLI subprocesses and perform network requests. * Sanitization: No explicit instructions for sanitizing or validating API-returned content before processing.
Audit Metadata