The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill executes git log to display history and git commit to save changes. These are standard operations for a version control tool and are used appropriately within the defined scope.
[PROMPT_INJECTION] (LOW): Potential for Indirect Prompt Injection through existing project data.
Ingestion points: SKILL.md ingests data from git log and references CLAUDE.md for project conventions. Both are external, potentially user-controlled sources.
Boundary markers: Absent. The agent is not explicitly told to ignore instructions embedded within commit messages or the configuration file.
Capability inventory: The skill allows the agent to execute shell commands (git add, git commit).
Sanitization: No sanitization or escaping is performed on the data read from the git history or project files before being presented to the agent's context.

git-commit