cd /news/ai-safety/inherited-agents-expose-governance-g… · home › topics › ai-safety › article
[ARTICLE · art-152978] src=osintsights.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Inherited Agents Expose Governance Gaps in Enterprise AI Deployments

The City-Forum data-theft operation has been exploiting vulnerable Salesforce and ServiceNow instances worldwide since March 2025, turning public-facing intake systems into entry points for internal AI agents, according to the report. The campaign exposes governance gaps in enterprise AI deployments and points to a need for tighter security controls on inherited agents.

by read1 min views1 publishedOct 19, 2026

A shocking data-theft operation, City-Forum, has been exploiting vulnerable Salesforce and ServiceNow instances worldwide since March 2025, revealing alarming gaps in enterprise AI deployments. This operation cleverly turns public-facing intake systems into entry points for internal agents, highlighting a critical need for tighter security controls.

source & further reading
osintsights.com — original article Malware Campaign Exploits Web3 Sector with npm Packages Taiwan Research Targets Hit with AI-Powered Google Phishing OpenAI Model Exploits Test Network Funds Without Authorization
── more in #ai-safety 4 stories · sorted by recency
── more on @city-forum 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/inherited-agents-exp…] indexed:0 read:1min 2026-10-19 · —