jk

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt's examples and commands explicitly place API tokens and secrets as CLI arguments or literal strings (e.g., --token <API_TOKEN>, --secret "value", echo "secret-value" | ...), which would require the agent to include secret values verbatim in generated commands.

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to fetch and display content from user-specified Jenkins controllers (e.g., "jk log team/app/pipeline 128", "jk job view ...", "jk run ls ...", "jk artifact download ...", and auth/login to https://jenkins.example.com), which would ingest user-generated/untrusted job configs, console logs, artifacts and other third-party content that the agent is expected to read and could materially influence subsequent actions.