Mega Skills Batch Creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): No instructions to bypass safety filters or ignore system prompts were found. The language is instructional and focused on project automation.
  • Data Exfiltration (SAFE): No network tools are requested (allowed tools are limited to Write, Read, Glob), and no sensitive credentials or exfiltration patterns are present.
  • Remote Code Execution (SAFE): No remote scripts, package managers, or external downloads are utilized. All operations are local to the file system.
  • Indirect Prompt Injection (LOW): The skill reads project files (CLAUDE.md, Makefile) and session history to generate new skills. While these sources could theoretically contain malicious instructions, the risk is inherent to the meta-programming task and no specific exploits are present.
  • Persistence Mechanisms (SAFE): The skill does not attempt to modify shell profiles, crontabs, or system startup settings.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:31 PM