speckit-implement

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill specification enables automatic execution of arbitrary commands defined in repository-controlled .specify/extensions.yml (pre- and post-hooks) and runs repo scripts, creating a clear remote code execution/backdoor vector that could be abused to exfiltrate data or compromise the system.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text via user input ($ARGUMENTS) and then directly reads multiple repo files (including .specify/extensions.yml and other task/specification files) from the current project without constraining authorship, so attacker-controlled text could be processed at runtime.