singular

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally from the npm registry. This is the official command-line tool used to interact with the Membrane platform.
  • [COMMAND_EXECUTION]: The instructions rely on executing shell commands via the membrane CLI to manage user authentication, establish connections to Singular, and run specific marketing actions.
  • [DATA_EXFILTRATION]: While the skill accesses external marketing data from Singular, it uses a centralized connection manager. It explicitly directs the agent to never ask for user API keys or tokens, relying instead on server-side OAuth flows.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes data retrieved from the Singular platform.
  • Ingestion points: Output from membrane action run (e.g., campaign names, reports, and metadata) in SKILL.md.
  • Boundary markers: None provided for the CLI output interpolation.
  • Capability inventory: Shell command execution via the membrane CLI in SKILL.md.
  • Sanitization: Not explicitly mentioned in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:27 PM