devtu-optimize-skills

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a high-level instructional guide for developers to improve the quality and reliability of AI agent skills. It emphasizes defensive programming, input validation, and rigorous testing.
  • [COMMAND_EXECUTION]: The documentation references the use of tooluniverse.cli for verifying tool schemas and testing implementations. These are standard development practices intended for local verification and quality control.
  • [EXTERNAL_DOWNLOADS]: The skill references several well-known scientific and bioinformatics databases, such as MyGene.info, HGNC (genenames.org), and NCBI, for the purpose of biological identifier resolution and data enrichment. These are trusted public research resources.
  • [PROMPT_INJECTION]: The instructions contain guidelines for agent behavior (e.g., 'Error messages must be actionable', 'No silent parameter dropping'). These are task-oriented constraints and do not contain any patterns intended to bypass safety filters or override system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 07:43 AM