speckit-clarify

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill reads and emits raw hook command strings from .specify/extensions.yml (including emitting EXECUTE_COMMAND: {command} and invoking those commands), so any credentials embedded in those commands would be printed or executed verbatim, creating an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill explicitly requires executing repository-defined hook commands and running local scripts and file writes (including mandatory "EXECUTE_COMMAND" invocations), which can be abused for remote code execution, backdoor insertion, and unauthorized repository modification if hook sources are untrusted.

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 mandates executing extension "hooks" (arbitrary commands found in .specify/extensions.yml) and requires writing/saving repo files (spec and checklists), which forces the agent to run external commands that can modify machine state or perform privileged actions.