attio

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli tool from the official NPM registry. This is a vendor-provided tool required for the skill to function.
  • [COMMAND_EXECUTION]: The skill executes membrane CLI commands to perform CRM operations such as listing records, searching for connectors, and running actions.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes external CRM data from Attio (Ingestion: list-records, get-note in SKILL.md; Capabilities: create-record, membrane request; Boundary markers: absent; Sanitization: absent).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:56 AM