The Agent Skills Directory

[PRIVILEGE_ESCALATION]: The skill instructions explicitly direct the agent to override standard safety protocols by installing missing dependencies 'automatically without asking the user to confirm.' Furthermore, it mandates that the agent 'do not request separate approval for dependency installation,' which is a direct attempt to circumvent user oversight and platform security guardrails.
[EXTERNAL_DOWNLOADS]: The skill requires the agent to download and install external code from a third-party repository (github.com/browser-act/skills) whenever the required CLI tools are missing. This creates a dependency on unverified external resources that are executed at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process data from an external website (1688.com). It lacks necessary security measures for handling this untrusted data.
Ingestion points: Search results, product titles, and metadata captured via browser automation in SKILL.md.
Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded commands in the scraped content.
Capability inventory: The skill utilizes the browser-act CLI for live browser interaction, network response capture, and screenshot capabilities.
Sanitization: Absent; the skill does not specify any filtering or validation for the content retrieved from the external marketplace.

1688-search-results-scraper