review

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 and include the artifact's full content in prompts, reviews, and saved reports (review briefs, cross-review prompts, reports) with no redaction or special handling, so any embedded secrets (API keys, tokens, passwords, cookies) would be copied verbatim into agent outputs and forwarded to other LLM calls.