The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes file diffs and contents to generate commit messages, creating an attack surface for indirect prompt injection where instructions embedded in code could influence the agent.
Ingestion points: File diffs and content read via git diff and the Read tool.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflow.
Capability inventory: Includes Bash, Read, Glob, and Grep tools as specified in SKILL.md.
Sanitization: No sanitization or validation is performed on the code content being analyzed.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute git commands, including git commit -m using messages derived from analyzed content.

commit