Skills
skills/avivsinai/telclaude/security-gate/Gen Agent Trust Hub

security-gate

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill does not define or use any tools, as indicated by the empty allowed-tools list.
  • [SAFE]: The instructions are focused on implementing security classification logic (ALLOW/WARN/BLOCK) to detect and prevent malicious inputs such as prompt injection and data exfiltration.
  • [SAFE]: No network access, file system operations, or remote code downloads are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 12:02 PM