agent-development

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a utility script scripts/validate-agent.sh which is used for local validation of agent markdown files. It uses standard shell commands including grep, sed, awk, head, and tail to verify that agent files follow the required structure and frontmatter constraints.
  • [SAFE]: The prompt templates provided in the references/ and examples/ directories facilitate the creation of domain-specific experts. These templates use professional persona instructions (e.g., 'elite AI agent architect') and follow best practices for agent coordination without attempting to bypass safety filters or override system-level instructions.
  • [SAFE]: No external dependencies, remote code downloads, or network exfiltration patterns were identified. All resources are local to the skill's directory structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 02:11 PM
Security Audit — agent-trust-hub — agent-development