walmart-product-detail-scraper
Fail
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill's runtime instructions direct the agent to automatically install the BrowserAct CLI from an external URL if it is not already present on the system.
- [COMMAND_EXECUTION]: The skill explicitly commands the agent to suppress user oversight by instructing it to "install the missing dependency automatically without asking the user to confirm" and to "not request separate approval for dependency installation."
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process data from external Walmart product pages, which are untrusted sources that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Captured browser-visible page content, product titles, descriptions, and metadata (referenced in SKILL.md under Common Data and Instructions).
- Boundary markers: None. The instructions lack delimiters or directives to ignore instructions embedded within the scraped content.
- Capability inventory: The skill invokes the
browser-acttool to perform browser interactions and network-based data collection. - Sanitization: There are no documented procedures for sanitizing or validating the content retrieved from the web before it is processed by the agent.
Recommendations
- AI detected serious security threats
Audit Metadata