agent-owasp-compliance

agent-owasp-compliance is an agent skill from the github/awesome-copilot collection that checks an AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10, the list of critical security risks specific to autonomous agents. The skill is for agents that call tools, access systems and act on behalf of users, rather than for chatbots that only produce text. Its purpose is to evaluate the security posture of an agent implementation by checking whether it addresses each of the ten risks. It applies when evaluating an agent system's security, when reviewing an agent before release, and when a team wants a structured check against a recognized industry list. The check looks at the code and configuration of the agent to see how each risk is handled, such as how tool access is limited, how inputs and outputs are controlled, and how the agent's actions are logged, and it reports which risks are addressed and which are not. The result is an assessment, not a certification: a passing check does not mean an agent is secure, and a failing one points to areas that need design or code changes. The skill is useful for security reviews of agent projects and for teams building a checklist for their agents. Findings should be reviewed by people with security expertise before they inform a release decision. The skill is installed with the skills CLI from the github/awesome-copilot repository. Its skills.sh page showed about 1.5K installs and passing results from three security audits at the time of the scan.…