ecommerce-review-scraper
Fail
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions designed to bypass user oversight and standard security consent prompts. It explicitly orders the agent to "install the missing dependency automatically without asking the user to confirm" and further commands the agent to "not request separate approval for dependency installation."- [EXTERNAL_DOWNLOADS]: The skill mandates the automatic installation of the "BrowserAct CLI" and a secondary agent skill from an external domain (browseract.com). This behavior introduces a supply chain risk by fetching and executing unverified third-party code without human review.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape and process arbitrary customer reviews from ecommerce websites, creating a vulnerability to indirect prompt injection where malicious content in a review could influence the agent's behavior.
- Ingestion points: Scraping of ecommerce product pages and reviews (SKILL.md).
- Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions embedded within the scraped data.
- Capability inventory: The skill utilizes the
browser-acttool which has network access and browser interaction capabilities. - Sanitization: Absent; the skill does not specify any validation or sanitization for the scraped content.
Recommendations
- AI detected serious security threats
Audit Metadata