The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on executing the vexor command-line utility. It instructs the agent to run search commands and diagnostic tools like vexor doctor and vexor config --show.
[INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface for indirect prompt injection because it reads and displays content from files within the local repository.
Ingestion points: File snippets and full contents returned by the vexor search command are loaded into the agent's context.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the searched files are provided in the skill instructions.
Capability inventory: The skill possesses shell execution capabilities for the vexor tool.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the files before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references an external prerequisite file (install-vexor.md) for tool installation. However, it explicitly instructs the agent not to run commands or procedures until the file is manually verified by the user, which serves as a security control.

vexor-cli