jk

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt shows commands that embed secrets verbatim (e.g., --token <API_TOKEN>, --secret "value", echo "secret-value" | jk ...), which would require the LLM to include raw secret values in generated commands or code.

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

• Third-party content exposure detected (high risk: 0.80). The skill's docs explicitly instruct fetching and ingesting uncontrolled Jenkins content (e.g., "jk job config" fetches raw config.xml, "jk log" streams console logs, "jk artifact download" and "jk run params" read job runs) from user-managed Jenkins controllers (SKILL.md and rules/job.md / rules/other.md), which are untrusted third‑party sources whose contents can be read and used to drive configuration or subsequent actions.