aquaria-cloudflare-ops

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

• Third-party content exposure detected (high risk: 0.80). The skill's update workflow instructs fetching and executing a public install script from raw.githubusercontent.com (see the curl -fsSL https://raw.githubusercontent.com/Alcyone-Labs/agent-skills/main/install.sh | bash commands in commands/droid/aquaria-cloudflare-ops.md and commands/opencode/aquaria-cloudflare-ops.md), which pulls and runs third‑party, user‑controlled content that can materially change tool behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill contains a runtime update/install step that explicitly runs a remote install script via curl piped to bash (https://raw.githubusercontent.com/Alcyone-Labs/agent-skills/main/install.sh), which fetches and executes remote code at runtime—this is a high-risk behavior.