The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local repository which can contain malicious instructions hidden in code comments or documentation.
Ingestion points: SKILL.md instructs the agent to run git diff and git status, which pulls file contents and names into the agent's active context.
Boundary markers: Absent. There are no instructions or delimiters used to separate the content of the changes from the agent's operational instructions.
Capability inventory: SKILL.md utilizes shell command execution to perform Git operations.
Sanitization: Absent. The skill does not provide mechanisms to sanitize or validate the data retrieved from the repository before processing it.
[COMMAND_EXECUTION]: The skill relies on the execution of shell commands, specifically git status, git diff, and git ls-files, to inspect and interact with the local file system.

commit