Notifications
Clear all
Topic starter
01/08/2026 10:42 pm
TL;DR: Agentic AI attacks are no longer theoretical, with STAR Labs reporting 1,700+ successful exploits against production agents, 36% of coding-agent attacks reaching remote code execution, and 91% of productivity-agent attacks ending in silent data exfiltration, according to Straikerai. The control problem has shifted from content moderation to runtime governance across apps, models, tools, MCP, and data.
NHIMG editorial — based on content published by Straikerai: STAR Labs Threat Report Volume I, "The Year Agents Entered the Workforce."
By the numbers:
- 36% of successful coding-agent attacks reached remote code execution
- 91% of successful productivity-agent attacks ended in silent data exfiltration
- 28.6% of cataloged MCP tools are high-risk by capability alone
Questions worth separating out
Q: What breaks when AI agents are given broad standing access?
A: Broad standing access breaks governance because the agent can move from one task to another without a fresh authorization check.
Q: Why do AI agents complicate zero trust in identity and access management?
A: Zero trust assumes continuous verification of who or what is requesting access, but AI agents can chain actions, infer context, and reuse privileges in ways traditional sessions do not.
Q: What do organisations get wrong about MCP security?
A: They often focus on network isolation or prompt filtering and miss the real issue: an authorised workload can still perform an unintended action.
Practitioner guidance
- Define agent-specific trust boundaries Separate agents that read, agents that write, and agents that execute.
- Inventory and govern MCP connectors List every MCP server, exposed tool, and downstream system the agent can reach.
- Treat agent credentials as high-risk NHI Map tokens, API keys, service accounts, and delegated access used by agents as non-human identities.
What's in the full report
Straikerai's full report covers the operational detail this post intentionally leaves for the source:
- The full STAR framework mapping across application, model, tools and MCP, and data layers for agent defence.
- The documented exploit patterns behind coding, productivity, and first-party agent compromise.
- The methodology section explaining how the 1,700+ successful exploits were tracked and classified.
- The five-control defender playbook for breaking the agent attack chain.
👉 Read Straikerai's threat report on agentic AI attacks and the STAR framework →
Agentic AI attacks are scaling fast - what do defenders do now?
Explore further
01/08/2026 10:52 pm
Agentic AI has created a new governance class, not just a new application type. The report shows that agents can move from reading context to taking action without a human in the loop at every step. That makes them closer to runtime identities than to static software features, which is why IAM and PAM assumptions now matter inside AI workflows. Practitioners should treat agent authorisation as a first-class governance domain.
A question worth separating out:
Q: How can organisations tell whether an AI agent is acting outside its intended scope?
A: Organisations should look for behaviour that crosses expected tool boundaries, generates unusual credentials, or chains actions across systems that are not part of the original task. The signal is not simply high activity. It is a change in action pattern, delegation, or downstream access context.
👉 Read our full editorial: Agentic AI attacks now target tools, data and code paths
