The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use ssh to execute commands on the remote host surrealdb.sh. This is the intended functionality for retrieving documentation in a terminal-based format.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from an external documentation source, which creates a potential surface for indirect prompt injection if the documentation were to contain adversarial instructions.
Ingestion points: Output from ssh commands such as cat, grep, and head described in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard embedded prompts within the retrieved documentation.
Capability inventory: The skill has the capability to execute shell commands via ssh and use local text-processing utilities.
Sanitization: No sanitization or filtering is performed on the documentation content before it is presented to the agent.

surrealdb-docs