editorial-portfolio-chapters
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data like brand names and project descriptions to generate a custom website layout.
- Ingestion points: SKILL.md instructs the agent to replace all placeholder content with original or client-provided content.
- Boundary markers: The instructions do not define specific delimiters to separate user content from agent instructions.
- Capability inventory: The skill is capable of generating functional HTML, CSS, and interactive JavaScript as seen in demo/index.html.
- Sanitization: There are no guidelines for the agent to sanitize or validate user-provided data before it is included in the generated output.
- [EXTERNAL_DOWNLOADS]: REFERENCES.md includes links to design inspiration on Framer, which is a well-known design and prototyping service.
- Evidence: Links to gaspar.framer.website are provided as design references.
Audit Metadata