openchoreo-developer
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies ingestion points for untrusted data, specifically when reading workload.yaml configuration files from Git repositories (documented in references/recipes/build-from-source.md) and container logs via the get_resource_logs tool (documented in references/recipes/inspect-and-debug.md). This data is used to inform deployment and configuration decisions.
- Ingestion points: Git repository configuration files (workload.yaml) and application container logs.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are specified for the processed data.
- Capability inventory: The agent has access to powerful tools via the openchoreo-cp MCP server, including create_component, update_workload, delete_component, and trigger_workflow_run.
- Sanitization: No explicit sanitization or validation of the content retrieved from logs or configuration files is described.
Audit Metadata