The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill processes git diff and status output, which are untrusted data sources that could contain adversarial instructions embedded in code comments or documentation.
Ingestion points: Git analyzer parses output from git status and git diff via git_analyzer.py.
Boundary markers: No specific delimiters or instructions to ignore embedded content were identified in the skill documentation.
Capability inventory: The skill is capable of reading repository files and executing git commit commands through batch_committer.py.
Sanitization: No sanitization logic for diff content was observed in the available partial source code.
[Command Execution] (SAFE): The skill performs command execution restricted to local git operations (git commit, git status, git diff). These operations are necessary for the skill's primary functionality and are triggered by explicit user requests.

git-batch-commit