landing-page-generator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of markdown instructions and structural templates for generating marketing copy. It does not perform any network operations, file system modifications, or command executions.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from project context files (e.g.,
.claude/project-context.md). While this is a data ingestion surface, it is a standard platform feature for providing project awareness to the AI agent. - Ingestion points:
.claude/project-context.md,.cursor/project-context.md. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The skill is limited to generating text, headlines, and page structures; it has no access to sensitive system tools or network capabilities.
- Sanitization: No specific sanitization or filtering of the context file content is described.
Audit Metadata