cloud-hunter

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs fetching cloud metadata and credential dumps (e.g., IMDS endpoints, lambda env vars, .env files, and verification requiring "credential dump"), which requires the LLM to handle and potentially output secret values verbatim, creating a high exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document is a clear offensive playbook: it instructs scanning and accessing public cloud storage, harvesting credentials from metadata endpoints and serverless env vars, exploiting overprivileged IAM roles for privilege escalation/role assumption, and exfiltrating sensitive data to external parties—actions that enable credential theft, remote compromise, and data exfiltration.