space-wechat-layout
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection and local cross-site scripting (XSS) based on the following evidence chain:
- Ingestion points: The skill collects untrusted article content from the user (SKILL.md, Step 1).
- Boundary markers: The instructions do not define delimiters or warnings to treat the article content as data rather than instructions.
- Capability inventory: The skill generates local HTML files and is authorized to execute shell commands for building and serving the project (SKILL.md, Step 7).
- Sanitization: There is no evidence of HTML sanitization or escaping when injecting user content into the {{ARTICLE_HTML}} placeholder in assets/static-preview-template.html.
- [COMMAND_EXECUTION]: The workflow explicitly directs the agent to run project build commands and start or reuse local development servers (SKILL.md, Step 7). This grants the agent the ability to execute shell commands within the project environment.
Audit Metadata