speckit-converge

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read fields from .specify/extensions.yml and emit them verbatim (e.g., Command: /{command}, Prompt: {prompt}, EXECUTE_COMMAND: {command}) and to actually invoke such commands, which will force any secrets embedded in those hook entries to be output or handled directly by the LLM.

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 running repository scripts and actually invoking mandatory extension hooks (pre- and post-converge), which can execute arbitrary commands from .specify/extensions.yml and thus may modify system files or require elevated privileges.