newebpay-query
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied input and external API responses, which can potentially introduce malicious instructions into the agent's context.
- Ingestion points: User input is captured via the $ARGUMENTS variable in SKILL.md, and transaction data is retrieved from the NewebPay API in references/code-examples.md.
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions within the processed data.
- Capability inventory: The skill is permitted to use Write, Edit, and Bash tools, which could be leveraged if an injection occurs.
- Sanitization: No evidence of input validation or output escaping is provided in the prompt logic for handling external content.
- [EXTERNAL_DOWNLOADS]: The skill makes network requests to official NewebPay API endpoints for transaction verification.
- Evidence: The code examples in references/code-examples.md configure requests to https://core.newebpay.com/API/QueryTradeInfo and https://ccore.newebpay.com/API/QueryTradeInfo.
Audit Metadata