velt-setup-best-practices
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE (SAFE): No malicious behaviors, obfuscation, or data exfiltration attempts were identified. The skill consists entirely of markdown documentation and code examples intended for developer education.
- EXTERNAL_DOWNLOADS (INFO): The installation instructions reference a repository under the anthropics organization (anthropics/agent-skills). This is a trusted source per [TRUST-SCOPE-RULE], and the npx command is used for legitimate skill deployment.
- PROMPT_INJECTION (INFO): The skill contains a large volume of rule-based instructions which constitute a theoretical indirect prompt injection surface (Category 8). However, because the skill provides no executable tools or functions, it possesses a negligible capability tier (INFO). Evidence: Ingestion points are the rules/ directory; no boundary markers; no capability inventory.
Audit Metadata