add-telegram

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

• Third-party content exposure detected (high risk: 0.85). The skill integrates a Telegram bot that receives and processes arbitrary user-generated messages from Telegram chats/groups (see "Channel Info" and the pairing/verification steps in SKILL.md), so untrusted third-party content can be ingested and influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches remote source during setup using "git fetch origin channels" (the configured origin repository URL) and installs @chat-adapter/telegram@4.26.0 from the npm registry (https://registry.npmjs.org/@chat-adapter/telegram), both of which pull external code at runtime that will be built/executed as part of the agent, so they constitute runtime external dependencies that can execute code.