fcode-ui-triggers
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an architecture where external data from the Factorial platform and user-editable forms are processed by agent scripts.\n
- Ingestion points: The skill receives external parameters via
fcode.context.parameters(such ascycle_id) and pre-filled fields in form-backed triggers as documented inSKILL.md.\n - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the ingested data are defined in the provided documentation.\n
- Capability inventory: Scripts can return data envelopes, trigger error messages displayed to users, and initiate subsequent processes via
nextProcessId.\n - Sanitization: The documentation explicitly notes that certain fields (like
company_idin the form path) are client-editable and should not be trusted for authorization, indicating that the input is not sanitized or trusted by default.
Audit Metadata