speckit-checklist

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). This skill instructs the agent to read .specify/extensions.yml and explicitly output hook command/prompt strings (and EXECUTE_COMMAND), which could cause any secrets embedded in those fields to be included verbatim in the LLM output — an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill specification allows automatic execution of repository-provided scripts/commands (pre/post hooks and a repo script), which enables remote code execution, supply‑chain abuse, and arbitrary data exfiltration if a malicious hook/script is introduced.

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 instructs the agent to execute repository scripts and to automatically run "mandatory" extension hook commands (EXECUTE_COMMAND), which could cause arbitrary system changes (including privileged actions) by executing commands defined outside the core prompt.