The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Bash to execute numerous git commands (git pull, git log, git diff, git branch, git status) and system utilities (find, awk) to analyze repository history and local notes. It also attempts to execute Google Chrome via a hardcoded path for PDF generation.
[EXTERNAL_DOWNLOADS]: It performs network operations through git pull to fetch data from remote repositories and uses npx to retrieve the md-to-pdf package from the npm registry.
[REMOTE_CODE_EXECUTION]: It invokes npx -y md-to-pdf, which downloads and executes a remote package at runtime to perform document conversion.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it ingest and summarizes content from git commit messages and local markdown files which are not fully under the agent's control.
Ingestion points: Commit messages retrieved via git log and daily records extracted from notes/daily_notes/ (SKILL.md).
Boundary markers: Absent; the skill does not use specific delimiters or instructions to prevent the agent from following commands that might be embedded in commit messages or notes.
Capability inventory: The skill has the capability to execute arbitrary bash commands, access the file system, and perform network requests.
Sanitization: No explicit sanitization or filtering is applied to the retrieved commit data or notes before they are processed for the final report.

git-review