The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the ability to execute various shell commands to perform its core functionality.
Evidence: Uses git status, git diff, git reset, git add, and git commit to manage repository state and history as described in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository (file changes and diffs) and then uses those inputs to plan and execute shell commands. This creates a surface for indirect prompt injection.
Ingestion points: Reads repository state via git status --short, git diff --cached --stat, and git diff --stat in SKILL.md.
Boundary markers: None. There are no delimiters or instructions provided to the agent to treat the content of the diffs as untrusted data or to ignore embedded instructions.
Capability inventory: The agent has the capability to execute shell commands (git add, git reset, git commit) based on its interpretation of the ingested data.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the git diffs before it is used to generate commit messages or select files for staging.

commit-buddy