The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from git diffs and context files while having file-writing capabilities.
Ingestion points: Git diff output and project-specific JSON context files.
Boundary markers: No explicit delimiters are defined in the instructions to isolate the diff content from the agent's instructions.
Capability inventory: The agent has access to Write and Edit tools, allowing it to modify the source code if the user confirms a fix.
Sanitization: No explicit sanitization or validation of the diff content is performed before processing.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard git commands for repository analysis. This includes git branch --show-current, git fetch origin main, and git diff origin/main. These operations are required for the skill's functionality and are used within a developer-facing context.

review