ads-readiness-assessment

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill defines a human-in-the-loop diagnostic process for website compliance and does not contain any malicious logic or hidden behaviors.\n- [PROMPT_INJECTION]: The skill is designed to process untrusted data from external URLs and local file systems (Step 1 and Step 5), which introduces a surface for indirect prompt injection. \n
  • Ingestion points: Website URL or local project path (SKILL.md).\n
  • Boundary markers: None specified.\n
  • Capability inventory: Parsing HTML/CSS/JS files, metadata, and site performance metrics (Workflow Step 2).\n
  • Sanitization: None specified. However, this surface is required for the skill's primary function of site auditing.\n- [NO_CODE]: The analyzed file is a markdown instruction set and does not contain any executable scripts, binary files, or package management configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 01:16 PM
Security Audit — agent-trust-hub — ads-readiness-assessment