NYC

anthropic-skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The shell script scripts/new_skill.sh is used to scaffold new project directories. It implements proper input validation using a regular expression to ensure that the skill name is in kebab-case, which mitigates risks of path traversal or command injection.
  • [EXTERNAL_DOWNLOADS] (SAFE): The documentation includes a reference link to an Anthropic resource (a trusted organization). No automated downloads or execution of remote scripts occur.
  • [DATA_EXFILTRATION] (SAFE): No patterns related to sensitive file access or unauthorized network transmissions were found.
  • [PROMPT_INJECTION] (SAFE): The instructions are focused on guiding the user through a design process and do not contain directives intended to bypass safety filters or override system constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 01:07 AM