steedos-object-fields

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, such as prompt injection, data exfiltration, or obfuscation, were detected in the skill instructions.
  • [COMMAND_EXECUTION]: The skill provides templates for defining JavaScript-based formulas (!!js/function) and Amis UI adaptors (requestAdaptor, adaptor). These are standard metadata configuration features of the Steedos platform intended for calculating record values and customizing the frontend user interface.
  • [PROMPT_INJECTION]: The instructions do not contain attempts to override agent behavior, bypass safety filters, or extract system prompts.
  • [DATA_EXFILTRATION]: No patterns of credential harvesting or sensitive data transmission to external domains were identified. The network references (e.g., /graphql) are internal to the platform's API architecture.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 05:46 AM