The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the git log command to extract commit history and statistics from local repositories under the ~/broomva/ directory.
[DATA_EXPOSURE]: It reads content from the user's local vault (~/broomva-vault/) and code repositories to identify modified files, completed tasks, and project activity for the purpose of generating a summary.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions.
Ingestion points: Reads user-authored markdown notes and git commit history from local directories.
Boundary markers: Not present; the instructions do not specify the use of delimiters to separate processed data from the agent's instructional context.
Capability inventory: Performs file system read/write operations and executes shell commands (git).
Sanitization: Not present; data is extracted and summarized without explicit filtering for embedded commands.

weekly-review