The Agent Skills Directory

[COMMAND_EXECUTION]: The skill defines several legitimate use cases for the x jina CLI tool, such as x jina reader for web parsing and x jina search for web queries. These commands are standard for the tool's intended functionality within the x-cmd ecosystem.
[PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to ingest and process untrusted data from external URLs and local files.
Ingestion points: External content is brought into the agent's context via the reader and search subcommands in SKILL.md.
Boundary markers: The instructions do not specify any delimiters or special handling to separate untrusted web content from the agent's core instructions.
Capability inventory: The agent can execute CLI commands and perform text analysis, but the skill does not grant elevated privileges or allow for arbitrary code execution from the retrieved data.
Sanitization: No explicit sanitization or filtering of the retrieved web content is implemented in the skill's logic.

jina