web-dev-explainer
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements an 'Anti-Patterns' section that explicitly instructs the agent to avoid treating external content, logs, or tool outputs as trusted instructions, which is a defensive measure against indirect prompt injection.
- [COMMAND_EXECUTION]: The documentation mentions a local Python script (
scripts/export-gemini-skill.py) for skill maintenance and suggests using the host's available execution tools for code demonstrations. These are functional instructions aligned with the skill's stated purpose as a developer tool.
Audit Metadata