opc-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates locally by managing session state within a dedicated 'opc-doc/' directory. It does not exhibit any network activity, perform external downloads, or access sensitive system credentials.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates a workflow that involves reading user-provided data from local files, creating a theoretical ingestion surface for indirect prompt injection.
- Ingestion points: Data is loaded from 'opc-doc/inputs/', 'opc-doc/outputs/', and 'opc-doc/state/' files.
- Boundary markers: The instructions do not define specific delimiters to isolate ingested file data from agent instructions.
- Capability inventory: The skill's capabilities are limited to local file system writes and orchestration of other domain-specific skills.
- Sanitization: No specific data sanitization or input validation logic is applied to the contents of the files being read.
Audit Metadata