redesign
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill specifies a requirement to execute
npm install @chenglou/pretextto facilitate text layout measurements during the redesign process. - [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves auditing and refactoring existing UI code, which serves as an ingestion point for potentially untrusted data that could contain malicious instructions.
- Ingestion points: Current UI code or site structure provided to the agent for auditing as defined in the Working Method section of SKILL.md.
- Boundary markers: Absent; the skill does not instruct the agent to use XML-style delimiters or clear "ignore embedded instructions" warnings when processing the source UI.
- Capability inventory: The skill can invoke package management tools (npm) and perform file system writes to update component code.
- Sanitization: Absent; there is no mention of sanitizing or filtering the source code before it is integrated into the agent's reasoning context.
Audit Metadata