venice-characters
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of documentation for the Venice AI API, covering character discovery and review management. It correctly uses environment variable placeholders for API keys and interacts exclusively with official service domains. No patterns of obfuscation, persistence, or privilege escalation were found.\n- [INDIRECT_PROMPT_INJECTION]: The skill describes methods for retrieving character descriptions and user-generated reviews, which are external, untrusted data sources. This constitutes a potential surface for indirect prompt injection if the agent processes this content without additional sanitization.\n
- Ingestion points: character metadata and review messages fetched from GET /characters and GET /characters/{slug}/reviews.\n
- Boundary markers: None specified in the documentation examples.\n
- Capability inventory: Network read access via curl.\n
- Sanitization: Not addressed in the skill's API examples.
Audit Metadata