speckit-constitution

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill instructs the agent to read external hook definitions and automatically invoke arbitrary hook commands (pre- and post-update), which creates a clear remote code‑execution/backdoor vector that can be abused for unauthorized actions or data exfiltration.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.90). The skill explicitly requires invoking arbitrary pre- and post-constitution "hook" commands discovered in .specify/extensions.yml (mandatory hooks "MUST" be run) and writes back files, which forces execution of external commands that can modify system state or require elevated privileges.