The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using the Bash tool, specifically agent-validate and git commit. These operations are fundamental to the skill's purpose of validating and versioning code changes.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via the $ARGUMENTS variable and processes output from the agent-validate tool to determine its execution flow. This creates a surface where specifically crafted inputs could attempt to influence the agent's logic or command construction.
Ingestion points: User input provided through $ARGUMENTS (SKILL.md) and tool output from agent-validate (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions to the agent to ignore embedded commands within the interpolated $ARGUMENTS or tool outputs.
Capability inventory: The skill possesses the capability to execute arbitrary shell commands and modify the file system via git (SKILL.md).
Sanitization: The instructions do not describe any sanitization, escaping, or strict validation of the $ARGUMENTS content before it is used for logic branching or interpolated into git commit commands.

validator-commit