opc-asset-ops
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from previous workflow stages stored in the
opc-doc/directory to generate asset plans. This creates a surface where content from earlier steps could influence current instructions.\n - Ingestion points: Reads files from
opc-doc/outputs/06-mvp-design/,opc-doc/outputs/07-conversion-loop/, andopc-doc/outputs/08-asset-ops/.\n - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the ingested file content.\n
- Capability inventory: The agent is authorized to use a 'Write' tool to create markdown files and update JSON state files in the
opc-doc/workspace.\n - Sanitization: No explicit validation or filtering of the input file content is defined in the instructions.
Audit Metadata