newsletter
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires installing the @membranehq/cli package globally via NPM. This tool is an official resource provided by the vendor to interface with the Membrane platform.
- [COMMAND_EXECUTION]: Executes shell commands using the membrane CLI to manage connections and run actions related to newsletter services.
- [DATA_EXFILTRATION]: Employs a secure authentication flow (membrane login) where credentials are managed server-side, preventing the agent from needing to store or handle sensitive API keys directly.
- [PROMPT_INJECTION]: The skill accepts natural language strings for intent-based searching and dynamic action creation, which presents a surface for indirect prompt injection if processed data is untrusted. Ingestion points:
--intentandaction createparameters in SKILL.md. Boundary markers: None present. Capability inventory: Ability to execute platform actions via the CLI. Sanitization: Not explicitly defined in instructions.
Audit Metadata