speckit-tasks

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires reading .specify/extensions.yml and explicitly emitting and invoking EXECUTE_COMMAND: {command} for mandatory hooks, which forces any command strings (potentially containing API keys or secrets) to be output verbatim, creating an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill manifest requires executing repository-provided scripts and "extension" hooks (including mandatory hooks) without evaluating their conditions and with silent parsing failures, enabling arbitrary command execution and a supply-chain/backdoor risk.

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 mandates running repository-provided scripts and actually invoking arbitrary extension hook commands (pre- and post-execution) from .specify/extensions.yml, which can execute arbitrary commands and thus modify or compromise the host system state.