signal-write

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a mechanism for an agent to communicate status by writing structured JSON files to a local .signals/ directory and appending entries to a markdown journal. All file operations are directed toward project-local paths.
  • [SAFE]: No network operations (e.g., curl, wget, fetch) or external data exfiltration patterns were detected. The skill operates entirely within the local environment.
  • [SAFE]: No remote code execution, package installations, or dynamic execution patterns (e.g., eval, exec) are present.
  • [SAFE]: The instructions do not contain prompt injection attempts, obfuscated content, or persistence mechanisms targeting the host system.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 07:52 AM
Security Audit — agent-trust-hub — signal-write