compute-management
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided OCI error logs and configuration requests, which serves as an ingestion surface for external data.
- Ingestion points: User queries regarding instance lifecycle, capacity errors, and shape selection (SKILL.md).
- Boundary markers: None present to delimit user input from instructions.
- Capability inventory: References OCI CLI commands for instance termination, IAM management, and resource querying (SKILL.md).
- Sanitization: No explicit validation or filtering of user-provided error messages or identifiers.
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to refer to official Oracle resources for up-to-date configuration.
- Fetches architecture guidelines from the oracle-terraform-modules organization on GitHub.
- References official Oracle Cloud Infrastructure API and documentation sites.
- [COMMAND_EXECUTION]: The skill provides specific OCI CLI commands for managing compute resources.
- References oci compute, oci limits, and oci iam commands for operational tasks (SKILL.md).
Audit Metadata