landing-page-generator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions guide the agent to read external project context files to inform the landing page generation process, creating a potential ingestion surface for untrusted data.
- Ingestion points: The file references
.claude/project-context.mdand.cursor/project-context.mdin the Initial Assessment section. - Boundary markers: There are no instructions to use delimiters or ignore instructions found within the external context files.
- Capability inventory: The skill is designed for text and layout generation, lacking dangerous capabilities such as file system writes or network access.
- Sanitization: No data validation or sanitization steps are defined for the ingested context.
Audit Metadata