OpenClaw

capability-composition-analyzer

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.

2.8k stars
openclaw/skillsskills/andyxinweiminicloud/capability-composition-analyzerMarch 14, 2026
View on GitHub

Install command

python "$CODEX_HOME/skills/.system/skill-installer/scripts/install-skill-from-github.py" --repo openclaw/skills --path skills/andyxinweiminicloud/capability-composition-analyzer
Tell me the task — I'll narrow the agent shortlist.