spacelift

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Membrane CLI (@membranehq/cli) from the public NPM registry. This is a routine operation for using the service's tooling and originates from a recognized vendor ecosystem.
  • [COMMAND_EXECUTION]: The skill uses local shell commands via the membrane executable to manage connections and execute actions. These commands are used for their intended administrative purposes within the Spacelift/Membrane context.
  • [DATA_EXFILTRATION]: No unauthorized exfiltration was detected. The instructions specifically guide users to avoid local secret storage, leveraging server-side OAuth flows instead.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) as it processes external data.
  • Ingestion points: Output from the 'membrane action run' command (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Shell command execution via CLI, network access (SKILL.md).
  • Sanitization: Not explicitly defined in the instructions. This is a common surface for integration skills and does not indicate malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 08:53 PM