database-management
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of Oracle Cloud Infrastructure (OCI) CLI commands to manage the lifecycle of database resources, including creation, scaling, and deletion.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating untrusted user data into system commands without providing sanitization or boundary marker instructions.
- Ingestion points: Placeholders like , , and in SKILL.md and references/oci-dbcs-cli.md are intended to be filled with user-provided data.
- Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore embedded instructions in the provided inputs.
- Capability inventory: The skill utilizes 'oci db' CLI commands which possess the capability to read, modify, and delete cloud infrastructure.
- Sanitization: Absent; the skill does not specify any validation or escaping mechanisms for the interpolated strings.
Audit Metadata