tangzhan-webpage-designer
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests arbitrary user text to generate HTML webpages, creating a potential vector for malicious content to influence the generated output. \n
- Ingestion points: User-provided text content is read and processed as the primary input as described in
SKILL.md. \n - Boundary markers: The prompt instructions for the coding model lack clear delimiters (e.g., XML tags or triple quotes) or 'ignore embedded instructions' warnings for the user-supplied content. \n
- Capability inventory: The skill is capable of generating full HTML files which can include executable JavaScript logic. \n
- Sanitization: There is no evidence of filtering or escaping logic applied to the user input before it is used in the code generation process.
Audit Metadata