vvvv-channels
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill documents methods for reading data from external files and application-wide channels, creating an indirect prompt injection surface.
- Ingestion points: The LoadScene example in 'examples.md' uses File.ReadAllText(filePath) to ingest external data.
- Boundary markers: No delimiters or safety instructions are included to mitigate potentially malicious content in the loaded data.
- Capability inventory: The skill showcases file reading and the ability to modify global application state via the IChannelHub.
- Sanitization: No evidence of path sanitization or value validation is present in the examples.
Audit Metadata