skills/steveclarke/dotfiles/critique/Gen Agent Trust Hub

critique

Warn

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the command npx impeccable to run a design audit tool from an external package registry.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the impeccable package from the npm registry at runtime using npx.
  • [REMOTE_CODE_EXECUTION]: The skill performs dynamic script injection by starting a local server and loading detect.js into the browser's execution context.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection.
  • Ingestion points: Processes local source code files and browser console messages in SKILL.md.
  • Boundary markers: No delimiters or instructions are used to separate untrusted file content from agent instructions.
  • Capability inventory: Capable of shell command execution, sub-agent spawning, and browser JavaScript execution.
  • Sanitization: No validation or sanitization of ingested content is performed before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 15, 2026, 12:51 PM
Security Audit — agent-trust-hub — critique