using-agent-skills

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text and workflow diagrams intended to guide agent behavior during software development.
  • [NO_CODE]: There are no executable scripts, shell commands, or external dependencies included in the skill. All content is descriptive markdown.
  • [PROMPT_INJECTION]: No evidence of prompt injection or attempts to bypass safety filters was found. The instructions focus on engineering best practices, such as surfacing assumptions and managing confusion.
  • [DATA_EXFILTRATION]: No network operations, sensitive file path access, or credential harvesting patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 10:32 AM