speckit-implement

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The document repeatedly instructs the agent to read and blindly execute hook commands from a repository-controlled YAML and to run repository scripts, which creates a clear remote code execution / supply-chain backdoor risk enabling data exfiltration or arbitrary command execution by an attacker who controls the repo content.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill mandates executing local scripts and actually invoking arbitrary extension hooks (pre- and post-implementation), and it also writes/creates repo files (ignore files), which forces the agent to run commands and modify filesystem state — creating a real risk of unintended or privileged system changes even though it does not explicitly request sudo or user creation.