adk-verify-snippets

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to copy the generated REPORT.md Executive Summary verbatim (SKILL.md:138-141) while the runner may execute snippets that use GEMINI_API_KEY/GOGLE_API_KEY (SKILL.md:37-44), so any secrets or tokens that end up in the report would be reproduced exactly by the LLM, creating an exfiltration risk.