chrome-extension-architect

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

• Third-party content exposure detected (high risk: 0.90). The skill's required install/update workflow (README.md and the command files such as commands/droid/chrome-extension-architect.md) explicitly instructs fetching and executing a script from raw.githubusercontent.com via curl (e.g., bash <(curl -fsSL https://raw.githubusercontent.com/.../install.sh)), which pulls public third-party content that the agent would ingest/execute as part of its workflow and could therefore supply untrusted instructions influencing behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill includes installation/update commands that fetch and execute remote shell scripts at runtime (e.g., bash <(curl -fsSL https://raw.githubusercontent.com/Alcyone-Labs/chrome-extension-agent-skill/main/resources/install.sh) and curl -fsSL https://raw.githubusercontent.com/Alcyone-Labs/agent-skills/main/install.sh | bash …), which executes remote code and thus is a high-risk external dependency.