The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python scripts (scripts/jenkins_deploy.py and scripts/run_tests.py) to interact with Jenkins APIs, manage build queues, and monitor execution status. These scripts are invoked via the command line with various parameters including JSON payloads.
[EXTERNAL_DOWNLOADS]: Installation instructions utilize npx add-skill to download the skill from the author's GitHub repository (github.com/ABCFed/claude-marketplace). This is a standard distribution method for this ecosystem.
[CREDENTIALS_UNSAFE]: The skill requires sensitive credentials (JENKINS_USER and JENKINS_TOKEN) to be stored in environment variables. While standard for Jenkins automation, these credentials grant access to the CI/CD environment and are recommended to be handled with caution.
[DATA_EXFILTRATION]: The skill transmits build parameters and authentication tokens to the remote Jenkins server at ci.abczs.cn. This network communication is essential for the skill's functionality.
[PROMPT_INJECTION]: The skill processes untrusted input from Git metadata (branch names, tags) and user-provided JSON strings for build parameters. While it lacks explicit sanitization documentation, this is a common attack surface for indirect prompt injection where malicious branch names could attempt to influence script behavior.

jenkins-deploy