skill-create

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to read project files and include "code examples from actual project files" in generated SKILL.md, which would cause the LLM to copy file contents (including any API keys/secrets) verbatim into its output.

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

• Third-party content exposure detected (medium risk: 0.30). In the skill-create from-btw {btw-id} path, the workflow reads outsider-authored suggestion text from .bkit/btw-suggestions.json at runtime and uses it as a seed for generating the new SKILL.md content.