dailybot

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests human-generated messages from the remote Dailybot API (e.g., GET https://api.dailybot.com/v1/agent-messages/ and the health check responses with "pending_messages" in messages/SKILL.md and health/SKILL.md) and requires the agent to read and act on those messages, so untrusted third‑party content can directly influence the agent's decisions and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The shared auth flow explicitly fetches and executes the installer script at runtime (curl ... https://cli.dailybot.com/install.sh and the PowerShell variant https://cli.dailybot.com/install.ps1 are downloaded and run after consent), which is remote code executed on the host.