apaas-object-schema
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides technical instructions for legitimate platform administration. It includes explicit constraints to protect system integrity, such as rules forbidding modifications to core system objects like
_userand_department.\n- [COMMAND_EXECUTION]: High-risk operations, such as deleting custom objects or fields, are documented with required safety parameters (e.g.,confirm: true) and standard operating procedures that mandate human verification after every write.\n- [PROMPT_INJECTION]: To prevent indirect prompt injection from untrusted data (like relational designs), the skill requires the agent to present a conversion table for user approval before creating any objects or fields from external inputs.\n- [DATA_EXFILTRATION]: No patterns of unauthorized data access, credential harvesting, or network transmission to external domains were identified; all operations are performed within the SDK and platform context.
Audit Metadata