The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various local shell commands such as git, find, awk, and Google Chrome to extract repository data, search for notes, and render documents.- [EXTERNAL_DOWNLOADS]: Downloads and runs the md-to-pdf package from the NPM registry using npx to facilitate the conversion of reports to PDF format.- [DATA_EXFILTRATION]: Uses git pull to update the local repository, which involves network communication with the user's configured remote repository providers.- [PROMPT_INJECTION]: Ingests potentially untrusted data from git commit messages and code diffs, creating a surface for indirect prompt injection.
Ingestion points: Outputs from git log, git diff, and local markdown notes in notes/daily_notes/.
Boundary markers: No specific delimiters or safety instructions are provided to the agent to treat commit content as untrusted data.
Capability inventory: Includes Bash tool access, file writing in the output/ directory, and network access for repository updates and package fetching.
Sanitization: The skill does not perform sanitization or validation of the commit messages before they are included in the analysis context.

git-review