opc-business-model-design
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files created in previous workflow stages, which represents a potential surface for indirect prompt injection if those files contain untrusted content.\n
- Ingestion points: Reads from
opc-doc/outputs/02-niche-positioning/*andopc-doc/outputs/03-value-proposition/*.\n - Boundary markers: The instructions do not define specific delimiters or "ignore" commands for the ingested data.\n
- Capability inventory: The skill utilizes a file "Write" tool to create and update files in the
opc-doc/directory.\n - Sanitization: There is no evidence of content sanitization or validation before the agent processes the input files.
Audit Metadata