cap-plugins

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install several official SAP CAP plugins using the @cap-js namespace from the NPM registry. These are standard, well-known dependencies for the SAP Cloud Application Programming Model.
  • [COMMAND_EXECUTION]: Provides standard npm install commands for package management. No suspicious piped execution, remote script downloads, or unauthorized command patterns are present.
  • [DATA_EXPOSURE_EXFILTRATION]: Contains examples of sensitive data handling (e.g., Social Security Number) specifically to demonstrate how to enable Audit Logging, which is a security best practice for PII. It does not contain any exfiltration logic or hardcoded credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill mentions the @cap-js/ai plugin and Model Context Protocol (MCP) exposure, but it does so in a descriptive manner for configuration purposes and does not introduce attack surfaces for prompt injection within the skill's own logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 06:11 PM
Security Audit — agent-trust-hub — cap-plugins