murlist

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the @membranehq/cli package to facilitate communication between the agent and the MurList API. This tool is managed by the skill's authoring organization.
  • [PROMPT_INJECTION]: The skill's primary function involves reading and managing shared lists from MurList. This creates an indirect prompt injection surface where malicious data stored in a list could influence the agent's behavior during processing.
  • Ingestion points: Data retrieved via membrane action run and membrane request (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are implemented for external data.
  • Capability inventory: The skill utilizes CLI-based network operations and element management.
  • Sanitization: No content validation or escaping mechanisms are specified for the incoming MurList data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 07:53 PM