html
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to the ingestion of untrusted repository documentation.
- Ingestion points: The skill is instructed to inspect files such as
AGENTS.md,CLAUDE.md, and design-system documentation within the user's workspace to derive design language and conventions. - Boundary markers: The instructions do not specify the use of delimiters or provide warnings to ignore natural language instructions that might be embedded within these documentation files.
- Capability inventory: The agent possesses the capability to write
.htmlfiles (containing potentially malicious JavaScript if influenced) and use browser tooling to open and exercise those files. - Sanitization: There is no evidence of content sanitization or validation for the data pulled from the repository environment before it is used to influence the agent's code generation logic.
Audit Metadata