regulatory-alert-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill leverages the SN-Execute-Background-Script tool to perform complex server-side data aggregation and impact analysis within ServiceNow. This is a legitimate use of administrative tools for processing high-volume GRC data that exceeds the capabilities of standard table APIs.
  • [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection by processing external regulatory alert data (e.g., alert descriptions).
  • Ingestion points: Data is retrieved from the description and short_description fields of the sn_regulatory_alert table in SKILL.md (Step 1 and Step 5).
  • Boundary markers: The instructions do not specify explicit delimiters for the agent to distinguish between external alert text and internal processing logic.
  • Capability inventory: The skill has access to SN-Execute-Background-Script, SN-Create-Record, and SN-Update-Record, which allow for significant platform modification.
  • Sanitization: There is no explicit validation or sanitization shown for the ingested alert content before it is processed by the background scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — regulatory-alert-analysis