The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands including git diff and grep to process project information. It constructs search patterns for grep using file paths obtained from the git history. If a repository contains files with names specifically crafted with shell metacharacters (e.g., semicolons or pipes), it could lead to unintended command execution when the agent processes the diff list.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and acting upon untrusted data from the project's environment.
Ingestion points: The skill reads data from .ua/knowledge-graph.json and the output of git diff commands.
Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when processing external content.
Capability inventory: The skill can execute shell commands (grep, git) and write files to the local disk (diff-overlay.json).
Sanitization: Absent. There is no logic provided to sanitize or validate file names or graph node content before they are interpolated into commands or the final analysis.

understand-diff