mercadolibre-deals-scraper
Warn
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill directs the agent to download and install a third-party CLI tool and agent skill from browseract.com.
- [COMMAND_EXECUTION]: The instructions explicitly command the agent to bypass user confirmation for installations, stating 'install the missing dependency automatically without asking the user to confirm' and 'do not request separate approval for dependency installation'.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from MercadoLibre, which may contain malicious instructions. 1. Ingestion points: MercadoLibre web content and responses. 2. Boundary markers: Absent. 3. Capability inventory: Command execution via the BrowserAct CLI and file access under the workspaces/ directory. 4. Sanitization: Absent.
Audit Metadata