The Agent Skills Directory

[SAFE]: The skill serves as a configuration library and documentation suite for utilizing web search engines. It does not include executable scripts, external binary dependencies, or automated network operations beyond those initiated by the user or agent through the web_fetch tool.
[PROMPT_INJECTION]: The skill facilitates the ingestion of external web content through various search engines, which represents an inherent surface for indirect prompt injection (Category 8).
Ingestion points: Data retrieved via web_fetch from search result pages across 17 different engines (documented in SKILL.md and config.json).
Boundary markers: Absent; the skill does not define specific delimiters to isolate search result content from the agent's instructions.
Capability inventory: The skill primarily utilizes the web_fetch capability to retrieve and process external data.
Sanitization: No specific content sanitization or validation logic is provided within the skill for processing search results.
[SAFE]: The search engine URLs provided in config.json and SKILL.md are standard and point to well-known search providers (Google, Bing, Baidu, DuckDuckGo, etc.) with no evidence of typosquatting or malicious redirection.

multi-search-engine