sla-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses REST API calls to interact with a ServiceNow instance (e.g., /api/now/table/task_sla). These network operations are directed at a well-known service and are necessary for the skill's primary function of SLA reporting.
  • [PROMPT_INJECTION]: The skill processes data from external sources (ServiceNow tables), which creates a potential surface for indirect prompt injection if those records contain instructions designed to influence the agent's behavior.
  • Ingestion points: External data enters the context from the task_sla and incident tables via the SN-Query-Table and SN-NL-Search tools.
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when it handles retrieved records.
  • Capability inventory: The agent has access to platform-native tools and ServiceNow-specific search tools to process and display the retrieved data.
  • Sanitization: There is no evidence of content sanitization or validation of the retrieved table fields (such as short_description) before they are presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — sla-analysis