agent-handoff

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within the intended user project directory, specifically creating documentation under the .claude/ subdirectory for task handoffs.
  • [SAFE]: The tool requirements (bash, view_file, write_to_file) are consistent with the skill's stated purpose of generating and managing markdown-based handoff packets.
  • [SAFE]: No remote code execution, external downloads from untrusted sources, or data exfiltration patterns were detected. The installation instruction uses a legitimate shorthand for a known skill manager (npx skills).
  • [SAFE]: The skill includes explicit security and privacy guidance in its examples, such as a 'Hard Constraint' instructing agents NOT to log sensitive data like customer card details or email addresses.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 05:04 PM
Security Audit — agent-trust-hub — agent-handoff