speckit-tasks

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill reads .specify/extensions.yml and prints hook command strings (e.g., /{command} and EXECUTE_COMMAND: {command}) directly into its output, which would force the LLM to reproduce any embedded secrets or tokens verbatim if present.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill spec instructs automatic execution of repository-provided scripts and “extension hooks” from .specify/extensions.yml (including emitting EXECUTE_COMMAND for mandatory hooks), which enables arbitrary command execution and supply-chain/backdoor risk if hook files or repository scripts are untrusted.