waitsec-pagemaker

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to perform 'Project Recon' by reading local project configuration files (e.g., package.json, manage.py, Gemfile, or wp-config.php) to identify the technology stack. This ingestion of untrusted local data creates a potential surface for indirect prompt injection if those files contain malicious instructions intended to influence the agent's code generation.
  • Ingestion points: Local project files scanned during the 'Part 0: Project Recon' step in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: The agent has file reading and writing capabilities to detect the project environment and generate new web pages.
  • Sanitization: No explicit validation or sanitization of the content within the detected project files is mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill defaults to using the Lucide icon library via the unpkg CDN (https://unpkg.com/lucide@latest) and mentions installing standard CSS frameworks like Tailwind CSS or Bootstrap through npm. These are established, well-known services for web development assets and do not pose a security risk in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 12:19 PM
Security Audit — agent-trust-hub — waitsec-pagemaker