migrate-custom-code
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes source code from an external SAP system and results from documentation searches, which could potentially contain malicious instructions intended to influence the agent's behavior during the fix generation process.
- Ingestion points: Source code retrieved via
SAPRead(Step 3a) and documentation/note search results (Step 3b, 3c). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' markers when passing retrieved source code or search content to the LLM.
- Capability inventory: The skill has significant write capabilities, including updating SAP source code via
SAPWriteand activating objects viaSAPActivate(Step 5). - Sanitization: There is no description of sanitization or validation logic for the content retrieved from external sources before it is interpreted by the agent.
Audit Metadata