draft-patterns

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Analysis of the skill instructions and configuration files found no malicious patterns, obfuscation, or unauthorized data access.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run python3 -m draft_agent.uiux, which is a vendor-owned CLI for searching UX patterns. This is an expected and legitimate use of the tool for this skill's purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes output from an external search tool, creating a surface for potential indirect prompt injection.
  • Ingestion points: Data returned by the draft_agent.uiux search command.
  • Boundary markers: None identified.
  • Capability inventory: Bash execution, file reading, and searching via Glob and Grep.
  • Sanitization: Output is constrained to a specific visual format template which helps confine and categorize the external data and reduces the risk of malicious instructions being followed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 02:47 PM
Security Audit — agent-trust-hub — draft-patterns