ui-ux-audit
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading application source code and data files to perform its audit functions. This allows for potential indirect prompt injection if the source code contains malicious instructions embedded in comments or strings.
- Ingestion points: Files located at
src/app/[target-page]/page.tsx,src/components/sections/[component].tsx,src/data/[related-data].tsx, andsrc/data/page-content/[page]-content.tsare read into the agent's context. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing these files.
- Capability inventory: The skill is limited to reading files and performing text searches (grep). It does not have capabilities for network operations, file writing, or administrative command execution.
- Sanitization: There is no evidence of sanitization or validation performed on the source code content before it is processed by the agent.
Audit Metadata