google-maps-category-lead-scraper
Warn
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The instructions contain explicit commands to override standard user-consent protocols. The skill directs the agent to install missing dependencies "automatically without asking the user to confirm" and further specifies that the agent should "not describe it as a request for the user to open their browser" and "not request separate approval for dependency installation."
- [EXTERNAL_DOWNLOADS]: The skill references external resources for dependency installation, specifically directing the agent to
browseract.comandgithub.com/browser-act/skills. While these target a known service, the instruction to perform these downloads silently and without authorization is a security concern. - [COMMAND_EXECUTION]: The skill requires the use of the
browser-actCLI. This involves executing shell commands at runtime to perform browser automation and lead scraping tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Google Maps (business names, categories, descriptions).
- Ingestion points: Data enters the agent context via browser scraping of external business listings in
SKILL.mdinstructions. - Boundary markers: None present; the skill does not instruct the agent to use delimiters or ignore instructions found within the scraped content.
- Capability inventory: The agent has the capability to execute shell commands via the BrowserAct CLI.
- Sanitization: No sanitization or validation of the scraped data is mentioned before processing.
Audit Metadata