skills/aladicf/better-web-ui/quieter/Gen Agent Trust Hub

quieter

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and acting upon untrusted data from the user's environment.
  • Ingestion points: The skill instructs the agent to analyze the current "codebase" and "design context" in the 'Assess Current State' section.
  • Boundary markers: There are no instructions to use delimiters or ignore embedded instructions when reading from the codebase files.
  • Capability inventory: The skill involves analyzing project files and systematically refining them, which implies the use of file read and potentially file write or code modification tools.
  • Sanitization: The instructions do not include any steps to sanitize, escape, or validate the content found in the codebase before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:53 AM