form-labels

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill consists of markdown files providing instructions and examples for accessibility best practices. No malicious patterns, obfuscation, or unauthorized data access were found.
  • [NO_CODE]: There are no scripts, binaries, or automated tools included in the skill files. All instructions are provided as natural language for the agent to follow.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reviewing external HTML and components. While this is an ingestion point for potentially untrusted data, the skill lacks any capabilities to execute or exfiltrate data based on that input.
  • Ingestion points: Reviewing rendered HTML, interactive components, or design-system patterns (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: None (no code or automated tools provided).
  • Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation from frontendchecklist.io and developer.mozilla.org. These are legitimate educational resources and do not involve automated downloads or execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 08:35 PM