The Agent Skills Directory

[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it reads and processes potentially untrusted data from git logs, commit messages, and modified file contents. Ingestion points: The skill uses git log and git diff outputs as primary context. Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the summary generation process. Capability inventory: The skill's capabilities are limited to text generation and ASCII diagramming; it does not have network access, file-writing permissions, or arbitrary code execution tools. Sanitization: No sanitization or filtering of the ingested git data or file content is described.
[COMMAND_EXECUTION]: The skill utilizes standard local git commands (git status, git log, git diff) to gather context for its summaries. These commands are diagnostic in nature and are used according to their intended purpose within a development environment.

progress-summary