accessibility
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided website code, which serves as a vector for indirect prompt injection where malicious instructions could be embedded in the data to influence agent behavior.
- Ingestion points: Ingests "网站代码" (website code) as defined in the
inputfield ofSKILL.md. - Boundary markers: The skill instructions do not specify the use of delimiters or clear separation between system instructions and user-provided code.
- Capability inventory: The skill does not request high-privilege capabilities such as arbitrary shell execution or network operations to non-whitelisted domains.
- Sanitization: No input sanitization or validation processes are mentioned for the source code being analyzed.
Audit Metadata