attio-core-workflow-a
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements strong safety boundaries by requiring explicit user approval for deletions and bulk operations. It also instructs the agent to verify record identities using exact IDs rather than ambiguous display names.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded credentials or secrets were found. The documentation correctly identifies the standard practice of using Bearer tokens in Authorization headers for API access.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests external data (schema definitions and record values), it mitigates risks by instructing the agent to reject unknown mappings and validate field shapes against the expected schema.
- [EXTERNAL_DOWNLOADS]: References point to official Attio documentation domains (docs.attio.com), which are well-known and trusted for the intended purpose of the skill.
Audit Metadata