jenkins-cicd

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill accepts Password-type parameters and shows tool invocations and GAIT logging that include "parameters" payloads (and confirmation prompts that print parameter values), so an LLM would likely need to emit secret values verbatim in generated tool calls or logs, creating an exfiltration risk despite a rule advising not to display tokens.

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflows explicitly retrieve and analyze untrusted, user-generated content — e.g., build logs via getBuildLog and searchBuildLog (Workflow 3) and SCM commits/repository data via getBuildChangeSets, getJobScm, and findJobsWithScmUrl (Workflow 4) — which the agent is expected to read/interpret and could materially influence troubleshooting and action decisions.