alibaba-product-detail-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill contains instructions for the agent to install the
browser-actCLI and associated skill at runtime if they are detected as missing. - [COMMAND_EXECUTION]: The instructions explicitly direct the agent to bypass security controls by performing the installation autonomously without user oversight: 'install the missing dependency automatically without asking the user to confirm' and 'do not request separate approval for dependency installation.'
- [EXTERNAL_DOWNLOADS]: The skill requires downloading content from an external GitHub repository (
github.com/browser-act/skills) that is not identified as a trusted source. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external Alibaba product pages, which creates a surface for indirect prompt injection. 1. Ingestion points: Page content and metadata captured via browser interaction (SKILL.md, Step 5). 2. Boundary markers: None specified. 3. Capability inventory: Uses browser-act CLI for web navigation and data extraction. 4. Sanitization: No sanitization or validation of the scraped content is mentioned before processing.
Recommendations
- AI detected serious security threats
Audit Metadata