jira-connector

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

• Third-party content exposure detected (low risk: 0.10). In the Jira connector’s runtime, the only outsider-authored free text it ingests comes from explicit user-provided parameters/files for comment/create/edit (e.g., --body-file, --description, --adf-file, --fields-json, --field), while reads (get, comments, search) just consume Jira issue/comment content selected by the user’s chosen issue key or JQL—there is no “queue/feed ingestion” path that an outsider can poison without the user selecting/fetching specific items.