skills/fradser/dotclaude/typeset/Gen Agent Trust Hub

typeset

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses instructional markers such as 'MANDATORY PREPARATION', 'MUST', and 'CRITICAL' to guide the agent through its design workflow. These are within the expected context of a technical task and do not attempt to bypass safety filters, extract system prompts, or override the agent's core instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill evaluates typography in user-provided content. While it lacks explicit boundary markers for user data, the skill's functionality is limited to providing design advice and CSS snippets. This presents a low risk of indirect prompt injection as it does not execute code based on the analyzed data.
  • [EXTERNAL_DOWNLOADS]: The skill references a local file reference/typography.md and a companion skill /impeccable. No external network requests or unauthorized downloads are present.
  • [COMMAND_EXECUTION]: The skill provides instructions for CSS properties and design system naming conventions. It does not perform any shell command execution or system-level operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 05:42 AM
Security Audit — agent-trust-hub — typeset