venice-api-keys
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows secure implementation standards by utilizing environment variables for secret keys and defining restricted scopes (INFERENCE vs ADMIN) for different access levels. No malicious intent, obfuscation, or persistence mechanisms were detected.\n- [EXTERNAL_DOWNLOADS]: All described network interactions target the official vendor domain at api.venice.ai, which is expected functionality for this skill's management purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill outlines operations that ingest and process structured data from external API responses.\n
- Ingestion points: Structured JSON data returned from endpoints at api.venice.ai (SKILL.md).\n
- Boundary markers: Not explicitly implemented in the provided documentation.\n
- Capability inventory: Execution of network requests via curl and fetch, and management of API credentials in the environment.\n
- Sanitization: The skill relies on structured JSON responses from the official vendor API.
Audit Metadata