The Agent Skills Directory

[SAFE]: The skill provides legitimate instructions for interacting with the Linkup Search API to perform web research and data extraction.
[SAFE]: Authentication is handled via the LINKUP_API_KEY environment variable. No credentials or secrets are hardcoded in the skill files.
[SAFE]: The skill directs network requests to the author's official domain, api.linkup.so.
[PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from the web, creating a potential surface for indirect prompt injection.
Ingestion points: Web search results and scraped page content (SKILL.md, references/LINKUP_API_REFERENCE.md).
Boundary markers: The instructions do not require the use of delimiters to separate retrieved content from the agent's instructions.
Capability inventory: The skill enables the agent to search the web and scrape arbitrary URLs.
Sanitization: There are no instructions for sanitizing or validating content retrieved from external web sources.
[NO_CODE]: The skill consists exclusively of markdown documentation and instruction files, containing no executable scripts, binaries, or automated code.

linkup-search