coding-html

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill handles potentially untrusted external content that could contain malicious instructions.
  • Ingestion points: Writing, editing, refactoring, or reviewing HTML and Jinja2 templates (SKILL.md).
  • Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions within the processed code data (SKILL.md).
  • Capability inventory: The skill utilizes web browser and browser_action tools (SKILL.md).
  • Sanitization: No evidence of sanitization or validation of the ingested content is provided (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 01:05 AM
Security Audit — agent-trust-hub — coding-html