TL;DR: Malicious agent skills can hide inside legitimate skill files and directories, letting attackers redirect agents into exfiltration, arbitrary code execution, and lateral movement, according to Starseer. Skill installation and precedence have to be treated as privileged decisions, because trusted content can carry active payloads.
Editorial analysis by NHI Mgmt Group, based on content published by Starseer: “Designing & Defending Against Malicious Agent Skills”.
Key questions
Q: Why do malicious agent skills create a greater risk than ordinary prompt injection?
A: They are more persistent and more operationally embedded.
Q: What are the signs that an agent skill is behaving maliciously?
A: Look for unexpected conditional branches, script execution that is not required for the stated task, requests to handle sensitive data in unusual ways, and agent actions that change from helpful processing to covert transmission or external calls.
Q: What breaks when AI agent skills are not reviewed before installation?
A: The main failure is that malicious instructions can hide inside a skill that appears legitimate, then execute under the agent’s delegated access.
Practitioner guidance
- Review skill bundles as executable content Inspect SKILL.md files, attached scripts, and resource files before allowing installation, and require approval for any skill that can invoke tools or scripts.
- Restrict automatic skill installation Disable silent or automatic skill rollout where possible so centrally managed skills cannot reach every agent without an explicit governance checkpoint.
- Scan for conditional data-triggered logic Look for instructions that activate only when sensitive data appears, especially branches tied to PII, PCI, PHI, or other high-value content.
Bottom line: Malicious agent skills turn trusted instruction bundles into a delivery mechanism for hidden behaviour, so the governance gap sits inside the skill lifecycle itself.
Glossary terms: Agent Skill, Skill Payload Smuggling, Pre-Emption, Conditional Exfiltration
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Malicious agent skills create a governance problem, not just a content-review problem. The attack surface is the packaging, distribution, and runtime interpretation of skill instructions, which means the control boundary moves from human review to agent execution. When a skill can influence scripts, tool selection, and conditional branches, the organisation is governing delegated authority rather than static documentation. Practitioners should treat skill onboarding as an identity and approval event, not a file import.
A few things that frame the scale:
- A May 2025 Gartner poll of 147 CIOs and IT leaders found that 24% had already deployed AI agents, 50% were experimenting and 17% planned to deploy by the end of 2026.
A question worth separating out:
Q: How should organisations govern agent skills in enterprise environments?
A: Treat skills as reusable knowledge packages that need classification, scope limits, and review just like other non-human identity assets. The important decision is not only what the agent can do, but what enterprise context it should be allowed to load in the first place. Skills should be segmented by task and sensitivity so that broad organisational knowledge is not exposed by default.
👉 Read our full editorial: Malicious agent skills expose a new path to AI hijacking