agent-telegrambot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit examples that embed Bot API tokens directly in commands and code (e.g., agent-telegrambot auth set <token>, curl "https://api.telegram.org/bot/...", login({ token: 'YOUR_BOT_TOKEN' })), which would require an LLM to handle and potentially 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 reads and processes user-generated Telegram messages via the Bot API (e.g., message commands and the SDK long-polling listener shown in "Real-Time Events" with listener.on('message', (msg) => { ... msg.text })) which are untrusted third-party contents that could contain instructions influencing agent behavior.