clean-oop-architecture
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a remote Git repository for a Unity dependency.
- Evidence: In
references/unity-oop.md, the instructions suggest proposing the installation ofhttps://github.com/furkantokkan/Onity.git#upm. - Context: The repository belongs to the skill author. The agent is explicitly instructed to ask for user permission before modifying any package files or project configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest content from local files and optional reference libraries which could contain instructions that influence agent behavior.
- Ingestion points: Local documentation at
docs/reference/private/coding/README.mdand external reference libraries accessed via search tools. - Boundary markers: The skill does not provide explicit delimiters or instructions to the agent to disregard potential prompts found within the documents.
- Capability inventory: The agent can modify source code and design project architecture based on the contents of the ingested files.
- Sanitization: The skill does not describe any validation or filtering mechanisms for the data retrieved from local files.
Audit Metadata