agent-messaging
Fail
Audited by Snyk on Feb 23, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.70). These are third‑party project pages (a dedicated domain plus two GitHub repositories) rather than official vendor sites; while GitHub is a reputable host, the skill instructs cloning and running an installation shell script from an unfamiliar repo and linking to a non-mainstream domain, which makes it potentially risky because arbitrary code could be installed or executed.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The Prerequisites instruct cloning and running an install script from https://github.com/23blocks-OS/ai-maestro-plugins.git (git clone ... && ./install-messaging.sh), which fetches and executes remote code at runtime and is presented as a required install for the CLI—so it can execute external code.
Audit Metadata