accelo

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the @membranehq/cli global NPM package. This is the primary interface for the integration and is a resource provided by the skill's vendor.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it acts as a bridge to external CRM data (Jobs, Issues, Tasks, etc.).
  • Ingestion points: Data enters the agent context via the membrane action run and membrane request commands when fetching records from Accelo.
  • Boundary markers: The instructions do not define specific delimiters or guardrails to distinguish between system instructions and data retrieved from the API.
  • Capability inventory: The skill allows the agent to execute subprocesses (via the CLI) to read, create, and modify data in the Accelo platform.
  • Sanitization: There is no evidence of sanitization or validation performed on the text fields retrieved from the external service before they are presented to the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:55 AM