cap-llm-plugin
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing official SAP AI SDK packages (
@sap-ai-sdk/langchain,@sap-ai-sdk/foundation-models) for Node.js inSKILL.md. - [PROMPT_INJECTION]: The code implementation in
SKILL.mddemonstrates the interpolation of user-provided content and retrieved document context directly into prompt templates. - Ingestion points:
req.datain theonAskQuestionhandler. - Boundary markers: Limited to simple text labels like
Context:andQuestion:without escaping or explicit instructions to ignore embedded commands. - Capability inventory: The skill uses the SAP AI SDK to perform chat completions and vector database searches.
- Sanitization: No sanitization or filtering logic is included in the examples, leaving the prompt vulnerable to indirect injection from processed data.
Audit Metadata