update-agent

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): No instructions found that attempt to override agent safety protocols or bypass constraints.
  • Data Exposure & Exfiltration (SAFE): The skill only interacts with local agent configurations and does not contain any network-enabled tools or hardcoded credentials.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): No external dependencies, scripts, or remote code patterns were detected.
  • Privilege Escalation (SAFE): While the skill can modify agent tool permissions, this is the primary intended function and is restricted to the local configuration directory under user supervision.
  • Persistence Mechanisms (SAFE): Modifications are limited to legitimate agent configuration files and do not include unauthorized startup or scheduling entries.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 08:22 AM