skillshare-ui-website-style
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by instructing the agent to process and enforce styles on files provided through the
$ARGUMENTSvariable. - Ingestion points: Content from files and areas identified by the
$ARGUMENTSinput inSKILL.md. - Boundary markers: The skill does not employ delimiters or specific instructions to isolate the data being processed from the agent's instructions.
- Capability inventory: The agent is expected to read and modify source code and style files in the
ui/andwebsite/directories. - Sanitization: No mechanisms for sanitizing or validating the content of the processed files are mentioned.
- [NO_CODE]: The skill contains only Markdown files and does not ship with any executable code, scripts, or binary files.
Audit Metadata