the-variant-router

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to generate text-based personalization strategies and measurement plans. It does not contain any executable code, shell commands, or network operations.- [DATA_EXPOSURE]: The skill reads from local configuration files like .agents/product-context.md and references/personalization-rules.md. These are standard practice for agent context and do not involve sensitive system files or credential exfiltration.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input and local context files to generate its output. While it lacks explicit boundary markers or sanitization for these inputs, the risk is negligible as the agent has no capabilities to execute commands or reach external networks based on malicious content within those files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:03 PM