ServiceNow agent discovery enabled cross-agent prompt-injection escalation
Review RAT-156 · Catalogue RAT-156
AppOmni primary says the researcher instructed a benign-looking agent to recruit privileged agents, illustrating controllable ServiceNow configurations. This is intentional exploit testing, with no documented live autonomous organizational incident.
Reviewed: · Rule: roguewatch-organizational-harm-v1
Dates and discovery
- Incident date
- Not disclosed
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- 2026-10-30T13:13:41.052493Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/appomni-servicenow-agent-discovery-injection/
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- Rogue AI Tracker discovery entryReporting / interview · rogueaitracker.com
- appomni.comOriginal account · appomni.com
Decision history
- · Case-by-case comparison audit
RAT-156: out-of-scope. AppOmni primary says the researcher instructed a benign-looking agent to recruit privileged agents, illustrating controllable ServiceNow configurations. This is intentional exploit testing, with no documented live autonomous organizational incident. Source checks: read: https://appomni.com/ao-labs/ai-agent-to-agent-discovery-prompt-injection/. AppOmni primary says the researcher instructed a benign-looking agent to recruit privileged agents, illustrating controllable ServiceNow configurations. This is intentional exploit testing, with no documented live autonomous organizational incident.
Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.