Topic starter
02/08/2026 11:58 am
TL;DR: Agent skill publishing surged 10x in weeks, from under 50 in mid-January to over 500 by early February, while malicious skills were already being distributed across Claude Code and OpenClaw ecosystems, according to Akto. The core problem is visibility and control over privileged agent extensions, not adoption speed.
Editorial analysis by NHI Mgmt Group, based on content published by Akto: “Introducing Skillguard in Akto Atlas: Detect and Govern Agent Skills Used by Employees”.
By the numbers:
- The agent skill publishing rate went from under 50 in mid-January to over 500 by early February, a 10x increase in weeks.
- Researchers at OpenSourceMalware.com reported the first coordinated malware campaign targeting Claude Code and OpenClaw users in February 2026, involving more than 30 malicious skills distributed via ClawHub.
Key questions
Q: What breaks when a malicious skill inherits an agent’s permissions?
A: What breaks is the assumption that authorised execution is also safe execution.
Q: Why do malicious skills create a bigger risk than ordinary code dependencies?
A: Malicious skills can influence what an agent does after load time, including tool selection, command execution, and data handling.
Q: How can security teams detect unsafe agent skills before they spread?
A: Teams need a combination of endpoint discovery and instruction inspection.
Practitioner guidance
- Build a live agent skill inventory Continuously enumerate every skill installed across employee endpoints, including who installed it, when it appeared, and which agent platform loaded it.
- Review skill instructions before execution Inspect SKILL.md contents for guardrail bypasses, workspace harvesting, and external data routing before allowing the skill to run.
- Restrict agent host permissions Reduce the file, shell, secret, and messaging permissions available to the host agent so a compromised skill inherits less authority.
Bottom line: Agent skills extend the authority of the host agent, which turns employee-installed helpers into governed access objects rather than harmless add-ons.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
02/08/2026 1:05 pm
Agent skills are becoming a governed identity surface, not just a software packaging format. The article shows that a skill inherits the permissions of the host agent, which means the control question is who or what is allowed to extend an agent’s authority. That moves skills into the same governance conversation as service accounts, tokens, and other non-human access objects. Practitioners should treat each skill as an identity-bearing extension of the agent runtime.
A few things that frame the scale:
- Only 5.7% of organisations have full visibility into their service accounts, according to the Ultimate Guide to NHIs.
A question worth separating out:
Q: Should organisations allow employees to install agent skills without review?
A: No, not if those skills can access files, credentials, or business communications through the host agent. Even a well-meaning productivity skill can become a data path if it inherits broad permissions. Review, allowlisting, and runtime policy are the minimum controls for employee-installed agent extensions.
👉 Read our full editorial: Agent skills need governance before malicious skills spread