plan-feature

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 1 explicitly fetches GitHub issue content ("gh issue view --json title,body,labels,state,number"), which ingests user-generated, public issue text that the agent must read and use to drive planning and decisions, creating a realistic vector for indirect prompt injection.