| name | capability-composition-analyzer |
| description | Helps identify dangerous capability combinations that emerge when agent skills are composed — catching the class of risk where no individual skill is harmful but their intersection creates an exfiltration or compromise path. |
Your Agent Has 12 Skills. Together, They Can Do Things None of Them Should.
Helps identify when individually benign skills compose into dangerous capability
combinations — the attack surface that per-skill auditing cannot see.
Problem
A skill that reads files is benign. A skill that sends HTTP requests is benign.
An agent that has both can exfiltrate files — and no individual skill audit will
flag it, because neither skill is doing anything wrong on its own.
This is the capability composition problem. Agent security tooling inherited from
software security tends to analyze skills in isolation: does this skill request
excessive permissions? does this skill contain malicious code? These are the right
questions for individual skills. They are the wrong questions for understanding
what an agent can do.
What an agent can do is the product of its capability set, not the sum of
individual skill assessments. An agent with twelve benign skills may have
emergent capabilities that no skill declared and no auditor reviewed. A poisoned
skill dropped into that composition inherits everything the agent can already
reach — and the blast radius is determined by the composition, not the skill.
The attack surface that matters is not what any individual skill can do. It is
what the agent's combined capability set enables.
What This Analyzes
This analyzer examines capability composition risk across five dimensions:
-
Dangerous pairs — Which pairs of capabilities in the agent's skill set create
risk when combined? read-files + send-HTTP, execute-code + network-access,
read-environment + write-logs are canonical examples. The analyzer checks for
known dangerous compositions and flags novel combinations that share structural
properties with them
