The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructs the agent to "install the missing dependency automatically without asking the user to confirm" and explicitly directs the agent to "not request separate approval for dependency installation." This is a direct attempt to override standard user consent and platform safety guardrails.
[EXTERNAL_DOWNLOADS]: The instructions mandate the download and installation of the browser-act CLI from an unverified external domain (browseract.com) and a GitHub repository (github.com/browser-act/skills). These sources are not recognized as trusted organizations or well-known services.
[REMOTE_CODE_EXECUTION]: By requiring the automatic installation and subsequent invocation of a third-party CLI tool, the skill enables the execution of unverified external code on the user's system.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is scraping web content, which serves as a significant ingestion point for untrusted data.
Ingestion points: Capture of browser-visible page content, visible metadata, and network responses from arbitrary Temu URLs (SKILL.md).
Boundary markers: No boundary markers or "ignore embedded instructions" warnings are defined to protect the agent's context from malicious data embedded in the scraped HTML.
Capability inventory: The agent is authorized to invoke the browser-act CLI and perform filesystem operations within workspaces/ (SKILL.md).
Sanitization: The skill lacks any instructions for sanitizing, escaping, or validating the external content before processing it or returning it to the user.

temu-category-listing-scraper