twg-jira

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

• Third-party content exposure detected (high risk: 0.75). The required workflow includes Jira workitem discovery/reads (e.g., jira workitem search/query and then jira workitem get), which at runtime ingests outsider-authored Jira issue text/snippets and comments from other users into the agent’s LLM context.