google-shopping-sku-ean-offer-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to download the 'BrowserAct' CLI and an additional skill from an external, untrusted domain (browseract.com).
- [REMOTE_CODE_EXECUTION]: The instructions mandate the automatic installation of a CLI tool. This process involves executing remote code or installation scripts on the user's system without prior verification of the software's integrity or contents.
- [PROMPT_INJECTION]: The skill contains specific directives to bypass standard user oversight and agent safety protocols. It instructs the agent to perform installations 'automatically without asking the user to confirm' and explicitly tells the agent 'do not request separate approval for dependency installation.' This is a concealment pattern designed to override the agent's transparency requirements.
- [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection due to its data processing workflow:
- Ingestion points: The skill ingests untrusted web content from Google Shopping during scraping operations (SKILL.md).
- Boundary markers: There are no instructions to use delimiters or ignore embedded directives within the scraped data.
- Capability inventory: The skill uses the 'browser-act' tool which allows for command execution and browser interaction.
- Sanitization: No sanitization or validation of the scraped content is performed before processing.
Recommendations
- AI detected serious security threats
Audit Metadata