consistent-border-radius
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill audits and rewrites user-provided frontend code files, which constitutes a data ingestion surface for untrusted content.
- Ingestion points: Processes external files (CSS, HTML, JSX, Vue, etc.) as described in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions to isolate user-provided code from agent instructions.
- Capability inventory: The skill is limited to text transformation and has no capabilities for network access, file system writes, or command execution, rendering the ingestion surface non-exploitable.
- Sanitization: No sanitization is performed on the audited content.
- [NO_CODE]: The skill contains no executable scripts, binaries, or configuration files that could run on the host system; it is composed entirely of markdown instructions.
Audit Metadata