pirate-weather

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the official Membrane CLI package (@membranehq/cli) via the npm registry to enable communication with the Membrane platform.
  • [COMMAND_EXECUTION]: The instructions utilize various membrane CLI commands for authentication, action management, and execution of weather data requests. These commands are localized to the tool's environment and intended functionality.
  • [PROMPT_INJECTION]: The skill allows for the creation of new actions based on natural language descriptions, which represents an indirect prompt injection surface.
  • Ingestion points: The DESCRIPTION argument in the membrane action create command in SKILL.md.
  • Boundary markers: No specific delimiters are defined in the instructions for the description input to prevent the agent from obeying instructions embedded in user data.
  • Capability inventory: The skill has the ability to run these generated actions via membrane action run.
  • Sanitization: Processing and validation of these descriptions are performed server-side by the Membrane platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 04:52 PM