speckit-clarify

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill reads .specify/extensions.yml and instructs the agent to echo hook fields (e.g., prompt, command, and an "EXECUTE_COMMAND" value) verbatim in its output, which can cause secret/API-token exfiltration if hooks contain credentials.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The prompt instructs the agent to run repository shell scripts, automatically execute extension hook commands from .specify/extensions.yml, and perform atomic writes to the spec file (FEATURE_SPEC), which causes the agent to modify the machine/project state and may execute arbitrary commands defined by extensions.