fill-template

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). This skill instructs the agent to read and print template content and to present exact phrase → token mappings (e.g. via print(read_content(...)) and the mapping list), which requires emitting verbatim text from the input files — so if those files contain secrets (API keys, passwords, tokens, etc.) the LLM would output them directly.