jenkins-agent

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's usage examples embed a JNLP secret token directly on the command line (e.g., -secret <SECRET_TOKEN>), which requires the LLM to place secrets verbatim into generated commands and creates an exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill includes runtime commands that download and then execute agent.jar from http://jenkins.example.com:8080/jnlpJars/agent.jar (curl/wget followed by java -jar), meaning it fetches and runs remote code that the skill relies on for operation.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill explicitly suggests "wrap in systemd service" (SKILL.md:56) and references installing/configuring agents and SSH keys (SKILL.md:15), which implies creating/modifying system service units and system-level configuration that can change machine state and require elevated privileges.