incident-response

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides templates for SN-Execute-Background-Script to perform administrative functions, including terminating active user sessions and resetting passwords via server-side JavaScript.
  • [DATA_EXFILTRATION]: The skill accesses highly sensitive ServiceNow tables such as sys_audit (audit logs), syslog (system logs), and hr_core_profile (human resources data). The data remains within the ServiceNow ecosystem and the access is necessary for the skill's core function of incident investigation.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.
  • Ingestion points: Data is pulled from untrusted sources like audit trails and system logs (SKILL.md).
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore malicious content within the logs during interpolation.
  • Capability inventory: The agent has access to sensitive data modification tools (SN-Update-Record) and code execution (SN-Execute-Background-Script).
  • Sanitization: There are no provided instructions for sanitizing or escaping the data retrieved from ServiceNow before it is used in prompt context or work notes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:23 PM
Security Audit — agent-trust-hub — incident-response