speckit-critique-run

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill reads extension hook entries from project YAML and instructs the agent to echo/execute the hook command verbatim (including EXECUTE_COMMAND: {command}), which could cause any embedded API keys or secrets in those commands to be output by the LLM.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill instructs executing repository-provided scripts and automatically running commands declared in extension hook YAML (including mandatory hooks executed without evaluating hook conditions), which creates a high-risk supply-chain / remote-code-execution vector that can be abused to run arbitrary code or exfiltrate data.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly instructs the agent to run repository scripts and automatically execute commands declared in .specify/extensions.yml (including mandatory hooks) without vetting, which can cause arbitrary state changes on the host (including privileged or destructive actions) even though it doesn't directly mention sudo or user-creation.