The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run git pull origin main within a specific local directory (~/code/void-sdk/void). This is a common development task to keep local files synchronized with a remote repository.
[DATA_EXPOSURE]: The agent is directed to access and read local files at ~/code/void-sdk/void/docs/ and ~/code/void-sdk/void/README.md to provide information about the framework.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by reading external data (the contents of the git repository) and executing shell commands, which could be exploited if the repository contains malicious content.
Ingestion points: Local files in ~/code/void-sdk/void/docs/ and README.md.
Boundary markers: Absent.
Capability inventory: Shell command execution via git pull.
Sanitization: None identified; the skill assumes the content of the pulled repository is safe to read.

void