TL;DR: Agent skills can become an access-control problem because their declarations can grant runtime authority, according to Tego AI. Capability text that is accepted automatically turns configuration into standing permission and needs review before deployment.
Editorial analysis by NHI Mgmt Group, based on content published by Tego AI: “The Hidden Layer: How Agent Skill Instructions Quietly Become Your Biggest Attack Surface”.
By the numbers:
- 1,437 skills combine at least one dangerous capability with no human approval gate whatsoever.
- 78.1% of indexed skills declare file system access.
- 76.0% of indexed skills declare code execution capability.
Key questions
Q: Why do AI agent skills create more risk than ordinary software packages?
A: AI agent skills inherit the permissions of the agent that runs them, so a malicious skill can act inside an existing trust boundary without needing to steal credentials first.
Q: How should security teams decide whether a skill needs human-in-the-loop controls?
A: Use human approval whenever the skill can change state, access sensitive data or call external tools on its own.
Q: What breaks when agent skills can request broad privileges without review?
A: The authorization model breaks first.
Practitioner guidance
- Audit declared skill capabilities Inventory every installed skill, compare each capability flag against the documented function and flag any mismatch as an authorization exception.
- Enforce human approval for dangerous actions Require human-in-the-loop approval whenever a skill can execute code, write files, handle credentials or reach external systems.
- Sandbox skill execution by default Run skills in isolated containers with minimal file, network and process access, and require documented approval for host-mode execution.
Bottom line: Agent skills are an access-control problem as much as an application problem, because their declarations can become the authority an AI agent uses at runtime.
Glossary terms: Agent Skill, Instruction-Layer Risk, Human-in-the-Loop (HITL), Capability Analysis
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Skill instructions are becoming the identity boundary for AI agents: the agent no longer waits for a separate permission decision when the skill file itself declares what authority it needs. That shifts governance from post-execution review to pre-load authorization, which is where most IAM programmes are weakest. The practical conclusion is that skill metadata is not descriptive text; it is effective access policy.
A few things that frame the scale:
- Systems with least-privileged AI access had a 17% incident rate vs 76% for over-privileged systems. Organisations failing to scope AI access properly are 4.5x more likely to experience a security incident, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
Q: What is the difference between prompt injection and instruction-layer risk in AI agents?
A: Prompt injection is an attack that manipulates an agent through hostile content it reads later. Instruction-layer risk is the unsafe authority the skill is given up front, often through a capability declaration that was never validated against need. One is adversarial manipulation, the other is unaudited design.
👉 Read our full editorial: Agent skill instructions expand the attack surface for AI agents