ui-copy

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data from numerous external sources, including locale files, CMS fixtures, and server responses. This provides an attack surface where malicious instructions could be embedded in data processed by the agent.
  • Ingestion points: The SKILL.md file specifies searching components, route data, constants, locale files, CMS fixtures, server responses, form schemas, and notifications.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested source data.
  • Capability inventory: The skill allows for file-system modifications ("Update the correct source of truth") and the execution of shell commands ("Run relevant build, typecheck, tests") as noted in SKILL.md.
  • Sanitization: There are no explicit instructions for sanitizing or validating the content retrieved from external sources before it is processed.
  • [COMMAND_EXECUTION]: The skill's verification protocol in SKILL.md instructs the agent to run project-specific build, typecheck, and test commands. These are standard operations within a software development environment and are appropriate for the skill's intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 06:57 AM
Security Audit — agent-trust-hub — ui-copy