The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill mandates the installation of the 'BrowserAct' CLI and skill from an external, non-whitelisted domain (browseract.com) and GitHub repository (browser-act/skills) whenever they are missing from the environment.
[PRIVILEGE_ESCALATION]: The instructions explicitly direct the agent to circumvent user consent workflows by stating it should "install the missing dependency automatically without asking the user to confirm" and "not request separate approval for dependency installation."
[EXTERNAL_DOWNLOADS]: The skill references an external installation link (https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main) to fetch third-party code. This source does not belong to a trusted organization or well-known service.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted content from the Lazada marketplace, which could contain malicious instructions.
Ingestion points: The skill captures browser-visible page content, metadata, and network responses from Lazada search results (SKILL.md, Instructions step 5).
Boundary markers: Absent. The skill does not provide instructions to delimit or ignore embedded instructions within the scraped product data.
Capability inventory: The skill has the capability to write data (cookies, account info, browser IDs) to the workspaces/ directory and perform network operations via the BrowserAct dependency (SKILL.md, Notes and BrowserAct Runtime sections).
Sanitization: Absent. There are no instructions to validate or sanitize the external data before returning it to the user.

lazada-search-results-scraper