newebpay
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input through the
$ARGUMENTSvariable to determine which sub-functional skill to suggest. - Ingestion points: User input is processed in
SKILL.mdto match integration keywords like "checkout", "query", or "refund". - Boundary markers: The skill does not use specific delimiters or instructions to ignore potential commands embedded within the user input.
- Capability inventory: The skill is primarily instructional and provides routing; it does not possess capabilities for file writing, system command execution, or network requests within its own logic.
- Sanitization: No input sanitization or filtering is performed on the provided arguments before the logic branch.
- [CREDENTIALS_UNSAFE]: The utility script
scripts/encryption.phpcontains hardcoded strings forHashKeyandHashIVin its example usage section. - Evidence: Lines 142-143 in
scripts/encryption.phpinclude specific 32-character and 16-character strings. While these correspond to publicly known test credentials from NewebPay's official documentation, hardcoding credentials in code samples can lead to accidental deployment of insecure configurations.
Audit Metadata