post-incident-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by processing external, untrusted data from ServiceNow security records.
  • Ingestion points: Steps 1, 2, 3, 4, 5, and 6 retrieve data from incident fields (descriptions, work notes, task outcomes, and audit logs) which could be influenced by an attacker during the incident lifecycle.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore potentially malicious commands embedded within the retrieved incident data.
  • Capability inventory: The skill utilizes high-privilege tools including SN-Execute-Background-Script, SN-Update-Record, and SN-Add-Work-Notes, providing a significant impact vector if an agent is manipulated via injected instructions.
  • Sanitization: No sanitization, filtering, or escaping processes are described for the external content before it is incorporated into analysis or used to generate metrics.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — post-incident-analysis