html-timeline-roadmap
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data to generate HTML artifacts, which represents a potential surface for indirect prompt injection.
- Ingestion points: Project names, lane categories, milestones, and status labels provided by the user in the prompt.
- Boundary markers: The skill does not define specific data delimiters but provides clear constraints to the agent regarding the structure of the output.
- Capability inventory: The generated HTML files include a mechanism to trigger the
Artifacttool via a JavaScript bridge (submitToClaude). - Sanitization: The instructions explicitly forbid the use of
innerHTMLfor any variable data, requiring the use oftextContentandcreateElementto mitigate XSS risks. - [EXTERNAL_DOWNLOADS]: The generated artifacts are permitted to load fonts from a well-known service for styling.
- Evidence: The skill allows the use of Google Fonts via the
<link>tag in the generated HTML.
Audit Metadata