agency-workflow-patterns

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflows explicitly call out fetching and ingesting GitHub/Jira issues and repository content (e.g., "Use Case: GitHub/Jira issue from start to finish", "Fetch all sprint issues", and the Explore agent "finds relevant files"), which are untrusted, user-generated third‑party sources the orchestrator/agents read and use to drive planning and execution.