Skills
Navigate
skills/arc-mcp/arc-1/generate-rap-logic/Gen Agent Trust Hub

generate-rap-logic

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions. 1. Ingestion points: Source code (BDEF, DDLS, CLAS) is read via SAPRead and implementation patterns are fetched via mcp-sap-docs. 2. Boundary markers: No delimiters or "ignore instructions" warnings are defined for the ingested data. 3. Capability inventory: The skill can modify methods using SAPWrite and deploy code with SAPActivate. 4. Sanitization: The instructions do not specify any validation or filtering of the retrieved system content.
  • [COMMAND_EXECUTION]: The skill uses SAPWrite and SAPActivate to modify and deploy business logic on the connected SAP system. While these are necessary for the skill's functionality, they represent high-impact operations on the target infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 01:14 PM