aicore-lifecycle-management
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local Python scripts to interact with the SAP AI Core API for resource lifecycle management tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data through deployment logs, creating a potential attack surface.
- Ingestion points: The
scripts/get_deployment_logs.pyscript retrieves log data from the SAP AI Core API. - Boundary markers: The skill does not use specific delimiters or instructions to ignore potential commands within the log output.
- Capability inventory: The skill provides full lifecycle management tools, including the ability to stop, delete, and patch deployments.
- Sanitization: There is no evidence of log message sanitization to prevent the agent from interpreting log content as instructions.
Audit Metadata