fsm-kb-generation
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests potentially untrusted data from external system fields and interpolates them into agent prompts.
- Ingestion points: The skill retrieves content from
sys_journal_field(work notes),wm_order(close notes), andwm_task(descriptions and close notes) via theSN-Query-Tabletool. - Boundary markers: The prompt generation logic in Step 8 lacks explicit delimiters or instructions to the AI to ignore embedded commands within the interpolated technician notes.
- Capability inventory: The skill possesses the capability to create and update records in ServiceNow using
SN-Create-RecordandSN-Update-Record, and identifiesBashas an available native tool. - Sanitization: There is no evidence of data sanitization, escaping, or validation performed on the external content before it is processed by the agent.
Audit Metadata