cc-connect

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill documentation includes example config entries with API tokens (Slack xapp/xoxb and a Telegram bot token) and an interactive "init" that collects platform credentials, which encourages embedding secrets verbatim into config or commands and thus requires the LLM to handle/output secret values directly.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md describes a runtime flow where free-form messages from an outsider (e.g., Slack/Telegram/Discord users) are routed through CC-Connect into the local Claude Code agent’s LLM context as the user’s command/prompt.