attio-upgrade-migration
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external documentation and OpenAPI specifications to guide code modifications, which creates a surface for indirect instructions. The risk is minimized by the use of official sources and structural checks.
- Ingestion points: Official Attio documentation and OpenAPI specifications retrieved via WebFetch.
- Boundary markers: None explicitly defined to separate external content from instructions.
- Capability inventory: Write and Edit tools used for local codebase modification.
- Sanitization: No explicit filtering or sanitization of the fetched documentation text.\n- [SAFE]: All external URLs point to well-known Attio official domains. The skill's operations align with its stated purpose of managing SaaS integration upgrades without suspicious behavior.
Audit Metadata