popup-cro

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text and marketing best practices related to popup and modal optimization. It does not include any executable scripts, shell commands, or network operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read a local configuration file (.claude/product-marketing-context.md) if it exists to gain project-specific context. While this is an ingestion point for external data, the skill uses this information solely to inform its text-based recommendations and lacks any dangerous capabilities (such as command execution or file writing) that could be exploited through injection. This is a standard pattern for context-aware developer tools.
  • [DATA_EXPOSURE]: There is no evidence of hardcoded credentials, sensitive file path access (beyond the localized project context file), or network exfiltration patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 04:27 AM