axiomui-audit
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process untrusted external data, specifically UI source code, computed styles, and component logic, to generate an audit report. Malicious instructions could be embedded within the source code being audited to influence the agent's findings or potentially impact downstream skills like
axiomui-website-upgradeif the report is passed to them. There are no explicit instructions for the agent to use boundary markers or sanitization when processing this untrusted input. - Ingestion points: Identified in
SKILL.mdunder Procedure Step 2, where the agent is instructed to gather evidence from the rendered UI and its source code. - Boundary markers: Absent from the instructions.
- Capability inventory: The skill is restricted to reading files and generating a markdown report; it explicitly states it does not edit code.
- Sanitization: No sanitization or filtering of the ingested source code is specified before analysis.
Audit Metadata