debug-jenkins

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes an explicit curl example passing admin: on the command line and instructs verifying/using Jenkins/MCP secrets (and potentially asking the user for a password), which would require the LLM to embed secret values verbatim into commands or outputs.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs the agent to call jenkins_mcp-get_build and jenkins_mcp-get_build_console_output to fetch console logs and Jenkinsfile contents from a user-provided Jenkins URL (e.g., jenkins.tpinf.xyz), which are untrusted, user-generated third-party content that the agent must read and interpret to decide failing stages, root causes, and follow-up actions.