pricing-page-generator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no executable scripts, shell commands, or remote dependencies. All content is educational markdown designed to assist an agent in generating copy and structural advice.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect injection by reading local project context files. Evidence: 1. Ingestion points: The 'Initial Assessment' section instructs the agent to read
.claude/project-context.mdor.cursor/project-context.md. 2. Boundary markers: Absent. 3. Capability inventory: None (the skill lacks scripts, network tools, or file-writing tools). 4. Sanitization: Absent. The risk is negligible as the ingestion is purely for personalization and the skill has no dangerous capabilities to exploit.
Audit Metadata