The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the execution of the jk CLI tool to perform all Jenkins-related tasks. This is the primary and intended function of the skill.
[EXTERNAL_DOWNLOADS]: The skill provides commands to install the jk CLI using Homebrew, Scoop, or Go, and points to the author's official GitHub repository (github.com/avivsinai/jenkins-cli) for binaries. These resources are from the verified vendor for this skill.
[CREDENTIALS_UNSAFE]: The documentation demonstrates how to pass API tokens and secrets via command-line flags. While this is a common pattern for CLI tools, the tool also supports reading secrets from standard input using the --from-stdin flag, which is a more secure practice.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external data from Jenkins, presenting a surface for indirect prompt injection.
Ingestion points: Data enter the agent's context through Jenkins console logs (via jk log) and build artifacts (via jk artifact download).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the logs or artifacts it processes.
Capability inventory: The skill grants the agent extensive control over Jenkins, including creating jobs (jk job create), modifying configurations (jk job configure), managing credentials (jk cred create-secret), and installing plugins.
Sanitization: No automated sanitization or validation of data retrieved from Jenkins is explicitly mentioned in the skill instructions.

jk