The Agent Skills Directory

[COMMAND_EXECUTION]: The skill explicitly requests and uses the Bash tool to execute ad-hoc tasks. This provides a capability for arbitrary shell command execution within the agent's environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon user-provided arguments and task descriptions. Because it possesses high-privilege capabilities (file system write access and shell execution), it is susceptible to indirect prompt injection if the data it processes (e.g., file contents or external inputs) contains malicious instructions targeting the agent.

gsd-quick