The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted content from external web searches. Ingestion points: search results are fetched in scripts/search.py from the configured SearXNG instance. Boundary markers: The skill does not implement delimiters or instructions to the agent to ignore embedded commands in the search snippets. Capability inventory: The skill uses urllib.request for network access in scripts/search.py. Sanitization: There is no sanitization or filtering of the content returned in search snippets.
[EXTERNAL_DOWNLOADS]: The skill performs outbound network requests to a remote SearXNG instance to fetch search results. The default instance is https://search.981234.xyz. This is the intended behavior of the tool but constitutes an external data dependency.

searxng-search