viral-product-evaluator

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to analyze content against a specific rubric (references/principles.md). It uses standard agent tools like grep and /browse to gather evidence based on user-provided inputs.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from landing pages and codebases. While this presents an indirect prompt injection surface (Category 8), the skill instructions are focused on critical evaluation and outputting a structured report, which aligns with safe operational practices for analysis agents.
  • [DATA_EXFILTRATION]: The skill identifies billing-related evidence in the codebase to evaluate monetization strategies. This behavior is scoped to the local environment and is consistent with the skill's stated purpose of auditing product virality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:53 PM
Security Audit — agent-trust-hub — viral-product-evaluator