aws-penetration-testing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs extracting, exporting, and passing AWS access keys, secret keys, and session tokens verbatim in commands and CLI arguments (e.g., --access-key/--secret-key, aws_consoler -a/-s, export AWS_*), which requires the LLM to handle secret values directly and poses exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These URLs include public S3 bucket patterns and a public bucket-indexing site (buckets.grayhatwarfare.com) which are commonly used to host arbitrary files (including malware), so they represent potentially suspicious download sources.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content provides explicit, actionable instructions to steal AWS credentials, exfiltrate data, escalate privileges, backdoor Lambda functions, gain persistence, and evade logging — representing high-risk malicious capability despite the stated authorization caveats.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill includes explicit privileged local commands (e.g., "sudo mkdir /mnt/stolen" and "sudo mount ...") and numerous instructions to create, modify, or delete cloud resources (create-access-key, attach policies, update Lambda code, delete CloudTrail, run SSM commands) which would change the state of the host or environment and enable persistent compromise.