plasmic

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or safety bypasses were detected. The skill uses standard CLI tools for its intended purpose.\n- [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the npm registry. This is a trusted vendor resource provided by the author to facilitate secure integration.\n- [COMMAND_EXECUTION]: Utilizes the membrane CLI to manage connections, discover actions, and run API requests. These commands are necessary for the skill's functionality and do not involve unauthorized privilege escalation.\n- [PROMPT_INJECTION]: The skill interacts with external Plasmic data, which serves as a potential surface for indirect prompt injection. No malicious payloads were found in the static content.\n
  • Ingestion points: Plasmic API responses and project content retrieved via membrane action run or membrane request (SKILL.md).\n
  • Boundary markers: None explicitly defined in the provided usage patterns.\n
  • Capability inventory: The skill uses the membrane CLI to read, search, and run actions which can modify Plasmic data (SKILL.md).\n
  • Sanitization: Relies on the Membrane platform's internal handling of API proxying and action execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 01:19 PM