skill-safety-audit

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional, providing a set of criteria and a workflow for detecting malicious instructions in third-party or updated skills. It does not perform any automated actions, file system modifications, or network communications.- [SAFE]: No obfuscation, hardcoded credentials, or remote code execution patterns were detected within the file content.- [SAFE]: Although the skill is designed to process untrusted data (other skills being audited), it lacks any executable capabilities that could be exploited via indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 04:04 PM