buildkite-api

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

• Third-party content exposure detected (high risk: 0.80). This skill instructs the agent to call Buildkite endpoints (https://api.buildkite.com and https://graphql.buildkite.com) and to ingest webhook payloads, job logs, build messages, and artifacts (see SKILL.md and references/webhooks.md), which are user-generated/untrusted content that the agent is expected to read and which can directly drive actions like triggering rebuilds.