popups
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides purely instructional content regarding marketing strategies, user experience, and conversion rate optimization for popups. No malicious command execution, data exfiltration, or obfuscation was found.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from local project files (e.g.,
.agents/product-marketing.md) for context. This is a standard architectural pattern for contextual AI agents and does not pose a risk in this instance as the skill lacks exploitable capabilities like file-writing, network operations, or shell execution. - Ingestion points:
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md. - Boundary markers: Not explicitly defined in the prompt interpolation.
- Capability inventory: None detected; the skill is limited to providing text-based recommendations and copy strategies.
- Sanitization: Not present, but the risk is negligible due to the absence of dangerous capabilities.
Audit Metadata