axiom-audit-liquid-glass

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a developer tool designed to audit Swift/SwiftUI codebases for the adoption of specific visual treatments. It functions by scanning local files for design-related patterns using established tools like glob and grep.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves reading and analyzing untrusted data from user-provided source code. While this represents a potential surface for indirect prompt injection, the risk is mitigated because the agent's instructions are restricted to generating reports and it does not possess tools for sensitive data exfiltration or system modification.
  • [METADATA_POISONING]: The metadata, including the name, description, and license, is consistent with the skill's stated purpose and contains no deceptive instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 10:44 PM