claude-to-im

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the agent to collect API tokens/secrets from the user and then write them into ~/.claude-to-im/config.env and run validation commands, which requires the LLM to include secret values verbatim in file contents and tool/command outputs.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly forwards messages from open/public IM platforms (Telegram, Discord, Feishu/Lark, QQ) to the Claude agent (see SKILL.md and README: "Messages from IM are forwarded to the AI coding agent"), and those user-generated, untrusted messages can trigger tool use (and even be auto-approved via CTI_AUTO_APPROVE), so third‑party content is read and can materially influence agent actions.