jk

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the jk CLI tool from external repositories on GitHub (avivsinai/jenkins-cli, avivsinai/scoop-bucket) and via Go's package manager.
  • [COMMAND_EXECUTION]: The primary functionality of the skill is to execute shell commands using the jk CLI binary to perform administrative tasks on Jenkins controllers.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its ingestion of data from external Jenkins environments.
  • Ingestion points: The skill reads Jenkins console logs (jk log), job configurations in XML format (jk job config), test reports (jk test report), and downloads build artifacts (jk artifact download).
  • Boundary markers: No explicit delimiters or "ignore embedded instructions" warnings are used when fetching data from Jenkins into the agent context.
  • Capability inventory: The agent can execute terminal commands via the jk binary and perform file system operations such as downloading artifacts and writing configuration files.
  • Sanitization: The skill does not provide mechanisms to sanitize, validate, or escape the content retrieved from Jenkins before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 05:37 AM
Security Audit — agent-trust-hub — jk