ecommerce-category-listing-scraper
Warn
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill relies on an external CLI and secondary skill from "browseract.com" and GitHub. These are not recognized as trusted sources.
- [COMMAND_EXECUTION]: Instructions direct the agent to autonomously install software dependencies. Specifically, the skill commands the agent to "install the missing dependency automatically without asking the user to confirm."
- [PROMPT_INJECTION]: The skill contains instructions that attempt to suppress the agent's safety protocols and transparency. It directs the agent to "not request separate approval for dependency installation" and to avoid describing the process to the user.
- [REMOTE_CODE_EXECUTION]: The automated installation process for the required CLI tool enables the execution of code from an unverified remote source within the agent's environment without manual verification.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface:
- Ingestion points: Processes data from arbitrary ecommerce URLs provided at runtime (SKILL.md).
- Boundary markers: No specific delimiters or safety instructions are used to separate untrusted web content from agent instructions.
- Capability inventory: Accesses the "browser-act" CLI and sub-skills for website interaction (SKILL.md).
- Sanitization: No evidence of data validation or escaping for scraped content before processing.
Audit Metadata