Malicious agent skills: what security teams need to act on

TL;DR: Agent skills can be backdoored to redirect AI agents into exfiltration, arbitrary code execution, and enterprise lateral movement, with attackers hiding malicious instructions inside legitimate skill files and directories, according to Starseer. Skill governance now has to assume that trusted agent content can carry an active payload, not just guidance.

Editorial analysis by NHI Mgmt Group, based on content published by Starseer: “Designing & Defending Against Malicious Agent Skills”.

Key questions

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.

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.

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.

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →