skills/akillness/oh-my-gods/ag-ui/Gen Agent Trust Hub

ag-ui

Warn

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to run npx create-ag-ui-app, which downloads the create-ag-ui-app package from the npm registry.- [REMOTE_CODE_EXECUTION]: By using npx, the skill immediately executes the downloaded create-ag-ui-app package, constituting a remote code execution pattern for unverified external code.- [COMMAND_EXECUTION]: The skill requires the Bash tool to perform scaffolding, installation, and environment initialization commands such as npx and package manager operations.- [PROMPT_INJECTION]: Analysis of indirect prompt injection surface:
  • Ingestion points: The agent architecture involves processing external event streams like TEXT_MESSAGE_CONTENT and STATE_DELTA (SKILL.md).
  • Boundary markers: There are no identified delimiters or warnings to ignore instructions embedded in the event data.
  • Capability inventory: The skill has access to powerful tools including Bash, Write, and Edit (SKILL.md).
  • Sanitization: The skill lacks explicit sanitization or validation protocols for the external data it processes.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 7, 2026, 08:19 AM
Security Audit — agent-trust-hub — ag-ui