attio

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill serves as a documentation guide for the Attio connector within the Apideck ecosystem. All logic and examples facilitate standard API operations through a known middleware provider.
  • [EXTERNAL_DOWNLOADS]: The skill references the official @apideck/unify Node.js package and provides links to official documentation and API specifications at apideck.com and attio.com. These are recognized vendor resources and do not pose a supply chain risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external CRM data (such as contacts, leads, and activities) from Attio.
  • Ingestion points: Data enters the agent context via the apideck.crm.contacts.list and related unified CRM methods (SKILL.md).
  • Boundary markers: None explicitly defined in the provided snippets.
  • Capability inventory: The skill facilitates network operations via the Apideck SDK and potentially through the Proxy API using curl (SKILL.md).
  • Sanitization: Not explicitly documented in the integration guide; standard SDK protections are assumed.
  • [CREDENTIALS_UNSAFE]: The skill correctly demonstrates using environment variables (process.env.APIDECK_API_KEY) and descriptive placeholders (e.g., your-consumer-id) rather than hardcoding sensitive credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 11:54 AM