freshservice

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from npm, which is the official tool for the Membrane platform.
  • [COMMAND_EXECUTION]: Uses the membrane CLI to perform authentication and execute Freshservice actions, which are the primary functions of this skill.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through data retrieved from Freshservice. Ingestion points: Tickets, agents, and requesters data fetched via actions in SKILL.md. Boundary markers: No specific delimiters or 'ignore' instructions are defined in the skill for these data points. Capability inventory: The skill can execute actions and web requests using membrane action run and membrane request as specified in SKILL.md. Sanitization: No explicit content sanitization or validation is implemented for retrieved ticket data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 11:12 AM