jitsu

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform operations such as managing connections, searching for actions, and executing API calls against the Jitsu platform.
  • [EXTERNAL_DOWNLOADS]: The instructions require the installation of the @membranehq/cli package via npm and the use of npx for action discovery. These are official tools provided by the skill's authoring vendor (membranedev).
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests untrusted data from external sources.
  • Ingestion points: CLI outputs from membrane action list, membrane connection list, and membrane action run in SKILL.md.
  • Boundary markers: The skill does not provide explicit delimiters or instructions for the agent to ignore potentially malicious instructions embedded in the retrieved data.
  • Capability inventory: The agent can execute CLI commands (membrane action run) and perform arbitrary network requests via the membrane request proxy.
  • Sanitization: No explicit sanitization or validation of the data retrieved from Jitsu is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 09:48 PM