The Agent Skills Directory

[SAFE]: The skill provides legitimate search engine URL templates and documentation for advanced search operators. All identified URLs point to well-known, trusted search providers.
[PROMPT_INJECTION]: The skill facilitates the ingestion of external search results, which inherently creates a surface for indirect prompt injection. This is a characteristic of the skill's primary function.
Ingestion points: The agent retrieves untrusted content from various search engine result pages using the templates in config.json and SKILL.md.
Boundary markers: Absent; there are no specific markers or instructions provided to the agent to treat search results as potentially untrustworthy.
Capability inventory: The skill utilizes the web_fetch tool to retrieve external data.
Sanitization: Absent; content is retrieved and processed as provided by the external search engines.

multi-search-engine