detect-conversation-type
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user input from conversation history to determine routing and perform record updates. * Ingestion points: Untrusted data enters via the
sys_cs_messagetable inSKILL.md(Step 1). * Boundary markers: Absent; no instructions are provided to distinguish between logic and retrieved content. * Capability inventory: AcrossSKILL.md, the skill can modify ServiceNow usingSN-Create-RecordandSN-Update-Record. * Sanitization: Absent; no methods for filtering or escaping user-provided text are defined. - [DATA_EXFILTRATION]: The skill accesses sensitive tables in ServiceNow, including
sn_hr_core_case(HR data) andinteractionlogs as defined inSKILL.md. This represents a data exposure surface for PII and internal communications.
Audit Metadata