agent-kakaotalk

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs AI agents to provide credentials via command-line flags (e.g., agent-kakaotalk auth login --email user@example.com --password mypass) and shows examples embedding oauth tokens/credentials in code/config, which forces the LLM to output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes user-generated KakaoTalk content (e.g., agent-kakaotalk message list / getMessages and chat list flows described in SKILL.md, references/common-patterns.md, and templates/monitor-chat.sh), and those third-party chat messages are read and used by agent workflows (monitoring, summarizing, and reacting), so untrusted messages could inject instructions that influence subsequent actions.