opc-value-proposition
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 located in the
opc-doc/directory to inform its analysis. - Ingestion points: Files such as
opc-doc/outputs/02-niche-positioning/segments.md,target-segment.json, andpositioning-statement.mdare read at startup (identified inSKILL.md). - Boundary markers: The instructions do not define explicit delimiters or 'ignore' commands for the content of these ingested files.
- Capability inventory: The skill has the capability to write multiple files to the local
opc-doc/directory and update state JSON files. - Sanitization: There is no mention of sanitizing or validating the content retrieved from these files before processing.
Audit Metadata