agent-development

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists primarily of educational content and structural templates for agent development.
  • [PROMPT_INJECTION]: The skill provides prompt templates in references/agent-creation-system-prompt.md and examples/agent-creation-prompt.md that interpolate user-provided descriptions.
  • Ingestion points: User-provided agent descriptions in the generation templates.
  • Boundary markers: Input is wrapped in double quotes.
  • Capability inventory: Agents created using these templates can access tools such as Read, Write, Grep, and Bash.
  • Sanitization: No sanitization is performed on user inputs before interpolation.
  • Analysis: This surface allows for indirect prompt injection if a user provides a malicious description, but it is a documented development pattern and assessed as safe within this instructional context.
  • [COMMAND_EXECUTION]: The skill includes a local utility script scripts/validate-agent.sh which uses grep, sed, and awk for file validation and does not execute arbitrary code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 04:45 PM