clawflow-inbox-triage

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation template for a message triaging workflow. It provides high-level patterns and TypeScript code snippets intended for implementation guidance rather than direct execution.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized command execution was found. The instructions focus on routing inbox items based on classification (e.g., business, personal).
  • [SAFE]: The skill references a local file path (skills/clawflow/examples/inbox-triage.lobster) for further examples, which is consistent with standard documentation practices and does not involve remote downloads from untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 06:06 AM
Security Audit — agent-trust-hub — clawflow-inbox-triage