axiomui-website-upgrade
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external website code, implementation details, and design patterns, which is a potential surface for indirect prompt injection.
- Ingestion points: The agent is instructed to "Inspect the current interface, implementation, and existing design patterns" and "Trace the cause" by inspecting components, styles, and tokens (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions that might be embedded in the code it analyzes.
- Capability inventory: The skill possesses the capability to modify repository files, including HTML, CSS, and component logic.
- Sanitization: No specific sanitization or filtering logic is prescribed for the data ingested from external website sources.
- [EXTERNAL_DOWNLOADS]: The skill provides fallback mechanisms to fetch design rules from the author's official web domain if local reference files are not available.
- Evidence: References to
https://axiomui.nischal.fyi/rules.jsonandhttps://axiomui.nischal.fyi/rules/<id>for rule lookups. - Context: These URLs are owned by the vendor and author (rexo77 / Nischal Skanda) and represent standard documentation resources.
Audit Metadata