wso2

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill documentation describes how to use the membrane CLI to execute actions and proxy requests, which creates a surface for indirect prompt injection if user-provided data is not properly sanitized before being passed to shell commands.
  • Ingestion points: User-supplied parameters for WSO2 actions and custom API endpoints provided in the membrane request command.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or provide guidance on ignoring embedded instructions within the processed data.
  • Capability inventory: The skill utilizes shell command execution via the membrane CLI, including action run and request capabilities in SKILL.md.
  • Sanitization: Absent; there are no instructions for validating, escaping, or filtering user-provided content before interpolation into the command strings.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the NPM registry. This is a vendor-specific tool required for the skill's operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 05:23 AM