opc-conversion-loop

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 stages to automate documentation and state management.
  • Ingestion points: The skill reads from opc-doc/outputs/06-mvp-design/* to gather context for the conversion loop design.
  • Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded in the ingested design files.
  • Capability inventory: The skill uses a Write tool to create and update multiple Markdown and JSON files within the opc-doc/ folder.
  • Sanitization: No specific sanitization or schema validation is applied to the ingested content before it influences the writing process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:21 AM