spark-cli-knowledge-sharing

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

• Third-party content exposure detected (high risk: 0.80). The skill requires running the spark query command as a mandatory pre-coding step to fetch recommendations from the shared Spark repository (user-contributed insights) which the agent must parse and use to guide coding and follow-up actions, exposing it to untrusted, user-generated third-party content via the Spark service.