The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx @useclawlink/cli, which fetches the ClawLink CLI from the public npm registry at runtime to perform authentication and execute search actions. This is a standard deployment method for the vendor's official tool.
[CREDENTIALS_UNSAFE]: The documentation discloses the local storage location for authentication tokens at ~/.clawlink/credentials.json. While it identifies a sensitive file path, it does not instruct the agent to exfiltrate or inappropriately access this data.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to retrieve and process content from various search engines (Baidu, Bing, Google, DuckDuckGo, eBay, etc.), which may contain adversarial instructions.
Ingestion points: Data is ingested through multiple search actions such as serpapi_bing_search, serpapi_duck_duck_go_search, and serpapi_get_facebook_profile.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided in the documentation to separate search result data from agent instructions.
Capability inventory: The skill possesses shell execution capabilities through the npx @useclawlink/cli interface.
Sanitization: The instructions do not specify any validation or filtering mechanisms for the external search data before it is processed by the agent.

serpapi