The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the nodes tool to execute curl commands. These commands are used to interact with the Jina Reader and Search APIs to fetch content.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to r.jina.ai and s.jina.ai. Jina AI is a well-known technology provider in the AI ecosystem, and these requests are used for its intended content-reading functionality.
[PROMPT_INJECTION]: The skill includes strong directives that attempt to override the agent's default tool selection by explicitly forbidding the use of api_calling, web browsers, or Python in favor of the nodes tool.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes content from arbitrary URLs without sanitization.
Ingestion points: Content retrieved from the r.jina.ai (Reader) and s.jina.ai (Search) endpoints (file: SKILL.md).
Boundary markers: None; the prompt does not provide delimiters or instructions to the agent to disregard commands embedded within the retrieved web content.
Capability inventory: The skill can execute curl commands via the nodes tool to fetch external data (file: SKILL.md).
Sanitization: None; the skill fetches content in raw markdown or JSON formats and passes it to the agent for processing.

jina-reader