pi-en

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to "ask directly" for human-held secrets and to run/verifiy external commands (curl/build/test) and "attach output" without any guidance to use environment variables or secure auth mechanisms, which can force the LLM to receive and emit secret values verbatim.