Notifications
Clear all
Topic starter
02/08/2026 11:35 am
TL;DR: Claude Skills introduces a package-like supply chain for AI agents, and researchers cited by Akto found 36.82% of skills contain security flaws while a separate analysis of 42,447 skills found 26.1% carry at least one vulnerability. The security gap is no longer theoretical: agent skills can spread silently, inherit broad runtime access, and evade conventional scanning.
NHIMG editorial — based on content published by Akto: 5 Claude Agent Skills Risks Every CISO Should Know
By the numbers:
- 36.82% of skills contain security flaws.
- 26.1% carry at least one vulnerability.
- A documented campaign saw 1,184 malicious skills flood a major registry.
Questions worth separating out
Q: What breaks when agent skills are added without central governance?
A: Security teams lose visibility into what has been installed, who approved it, and which runtime context it can reach.
Q: Why do agent skills increase privilege escalation risk in enterprise environments?
A: Because many skills inherit the agent's full runtime context, including credentials, file access, and network permissions.
Q: What do security teams get wrong about reviewing community AI agent skills?
A: They often review the visible text and forget that the agent reads raw content, not a rendered browser view.
Practitioner guidance
- Inventory all installed agent skills Map skills across workstations, claude.ai tenants, and API-based deployments, then assign an owner and lifecycle state to each one.
- Require provenance and signing for skills Block unverified skill sources, enforce source review for SKILL.md content, and pin approved versions so a later update cannot silently change behaviour.
- Scope agent permissions per skill or task Separate file access, network egress, and credential exposure by workflow so one approved skill cannot inherit the full runtime context of the agent.
What's in the full article
Akto's full blog covers the operational detail this post intentionally leaves for the source:
- The per-category breakdown of the five Claude Skills risk areas and the OWASP AST10 mapping used to classify them.
- The environment discovery example showing how 400+ agent skills were found on workstations the security team had not mapped.
- The proof-of-concept and registry abuse examples that illustrate malicious payload delivery, privilege inheritance, and platform portability.
- The article's specific references to CVEs, registry flooding, and multi-platform risk propagation that help teams plan detection and response.
👉 Read Akto's analysis of Claude Skills security risks for agentic systems →
Claude Skills risks and the governance gap for agentic security?
Explore further
02/08/2026 12:48 pm
Agent skills are becoming a shadow NHI layer: a skill is effectively a delegated capability that can operate with access to tokens, files, APIs, and network paths. That makes it closer to a non-human identity than a simple plugin. Organisations that manage agents as software but ignore their delegated authority will miss the real governance boundary. Practitioners should treat skills as identities with scope, provenance, and lifecycle controls, not as harmless add-ons.
A question worth separating out:
Q: How should security teams govern portable agent skills across multiple platforms?
A: Use a single trust policy for provenance, signing, version pinning, and revocation across every platform that can load the skill. If a skill behaves differently by platform, treat that as a control failure, not a convenience feature. The goal is to make trust portable only when governance is portable too.
👉 Read our full editorial: Claude Skills security risks expose a new agentic supply chain
