Skills
skills/vm0-ai/vm0-skills/attio/Gen Agent Trust Hub

attio

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl to interact with api.attio.com, a well-known service. It also includes instructions for using zero doctor to verify the environment.
  • [DATA_EXFILTRATION]: Instructions specify writing request data to /tmp/ before sending it via curl. This is a routine method for data handling and no exfiltration to unauthorized destinations is observed.
  • [PROMPT_INJECTION]: As a CRM integration, the skill ingests data that could serve as a surface for indirect prompt injection. Ingestion points: Endpoints for reading CRM records and notes in SKILL.md. Boundary markers: None. Capability inventory: curl for network operations and local file writing. Sanitization: Not explicitly defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 02:45 AM