add-telegram-swarm

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks the user to paste sensitive secrets (Telegram bot tokens and a Gemini API key) and instructs the agent to insert them verbatim into .env or shell commands (e.g., TELEGRA M_BOT_POOL, GEMINI_API_KEY), requiring the LLM to handle and output secret values directly, which is an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill contains deliberate, high-risk behaviors: it instructs storing Telegram bot tokens and other API keys in .env/launchd and adding them to container allowlists so containerized agents receive live credentials, and it implements dynamic bot renaming which enables impersonation — together these create clear avenues for credential theft, data exfiltration, and abuse by remote agents.