propeller

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform integration tasks such as connecting to Propeller, listing actions, and running them. This is the intended operation of the skill.
  • [EXTERNAL_DOWNLOADS]: Instructs the user to install the official @membranehq/cli package from the npm registry, which is a well-known and trusted source.
  • [PROMPT_INJECTION]: The skill interprets user intent to discover and execute actions within the Propeller environment. This represents an indirect prompt injection surface.
  • Ingestion points: User-provided intent and description strings in SKILL.md.
  • Boundary markers: None present in the command examples.
  • Capability inventory: Execution of actions via membrane action run.
  • Sanitization: Handled server-side by the Membrane platform.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 01:13 PM
Security Audit — agent-trust-hub — propeller