qiita

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

• Third-party content exposure detected (high risk: 0.80). The skill directly fetches and displays user-generated content from the public Qiita API (https://qiita.com/api/v2) — e.g., cmd_item_search/cmd_item_get and cmd_comment_list in scripts/qiita.sh and the SKILL.md describe searching and reading articles and comments — which are untrusted third-party sources that the agent reads and could use to influence subsequent actions.