billing-integration
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation and code examples from the vendor's official resources.
- Evidence: https://docs.credyt.ai/ai-integration.md, https://github.com/credyt/learn
- Context: These resources are used to provide the agent with implementation patterns and examples for the integration task.
- [PROMPT_INJECTION]: The skill's workflow involves reading and modifying user-provided source code, which represents an indirect prompt injection surface.
- Ingestion points: Application codebase (SKILL.md, 'Understand the codebase first' section).
- Boundary markers: Absent. There are no instructions to disregard potential commands found within the codebase being analyzed.
- Capability inventory: The agent is tasked with file reading and modification.
- Sanitization: Absent. The content read from the user's project is processed without validation for embedded instructions.
- [NO_CODE]: This skill consists of markdown instructions and does not include any accompanying scripts or binary files.
Audit Metadata