skill-creator-agnostic

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements strong security and stability practices, such as mandating the use of temporary workspaces ($env:TEMP) to prevent accidental modification or exposure of source code repositories.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of local Python and PowerShell scripts (e.g., aggregate_benchmark.py, generate_review.py, and validate-skill-templates.ps1). These executions are strictly scoped to the local environment and are necessary for the skill's stated purpose of benchmarking and validation.
  • [EXTERNAL_DOWNLOADS]: The skill references an external dependency on the 'skill-creator' tool from Anthropic. This is documented as a prerequisite and follows the established workflow for the vendor's ecosystem.
  • [PROMPT_INJECTION]: No patterns associated with direct prompt injection or instructions to bypass safety guidelines were found. The skill uses structured data for evaluations, which minimizes the risk of indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 01:56 PM