landing-page-designer

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation, or unauthorized access patterns were found within the skill file. The skill instructions focus on design principles, copy editing, and tool usage for research purposes.- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process data from external research results provided by Perplexity. This is a standard functional requirement for search-enabled agent skills.
  • Ingestion points: External data enters the context via mcp__perplexity__search or mcp__perplexity__reason (SKILL.md).
  • Boundary markers: Absent. The skill does not define specific delimiters to wrap research data or instructions to the agent to ignore embedded commands in search results.
  • Capability inventory: The skill is limited to generating landing page copy and React-based frontend components; it does not have access to file-system writes, shell execution, or sensitive network operations.
  • Sanitization: Not present. Research data is mapped directly to section sections.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 06:35 AM
Security Audit — agent-trust-hub — landing-page-designer