skill-creator

Fail

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: CRITICAL
Full Analysis
  • [SAFE]: The skill provides procedural guidance and automation for skill development. All operations are confined to the local filesystem for creating directory structures and zipping files.
  • [COMMAND_EXECUTION]: The provided Python scripts (init_skill.py, package_skill.py, quick_validate.py) perform legitimate filesystem operations such as directory creation, file writing, and archiving. They do not accept unsanitized shell input or execute arbitrary system commands from external sources.
  • [DATA_EXFILTRATION]: There are no network-capable functions (e.g., requests, urllib, curl) or patterns suggesting the collection or transmission of sensitive data.
  • [PROMPT_INJECTION]: The instructions in SKILL.md and the reference files focus on structural formatting and clear communication. They do not contain instructions aimed at bypassing AI safety filters or overriding system prompts.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 24, 2026, 11:23 AM