push-by-techulus

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the Membrane CLI tool from the public npm registry (@membranehq/cli). This is a documented dependency provided by the skill's author to facilitate the integration.
  • [COMMAND_EXECUTION]: The instructions utilize the membrane command-line interface to manage authentication, establish connections to the service, and execute API actions. These operations are restricted to the functional scope of the integration.
  • [DATA_EXFILTRATION]: The skill possesses an attack surface for indirect prompt injection as it ingests data from external Push by Techulus endpoints.
  • Ingestion points: Data is retrieved via membrane action run and membrane request commands (SKILL.md).
  • Boundary markers: None explicitly defined in the provided instructions.
  • Capability inventory: The agent can execute shell commands via the Membrane CLI and perform network operations through the proxy (SKILL.md).
  • Sanitization: No explicit sanitization of the retrieved notification data is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 03:19 AM
Security Audit — agent-trust-hub — push-by-techulus