The Agent Skills Directory

[SAFE]: The skill operates locally to facilitate session handoffs, using Git metadata to populate a progress summary. It does not perform network operations, access sensitive credentials, or attempt to persist across sessions.
[COMMAND_EXECUTION]: Employs standard shell commands including git status, git log, date, and mkdir to retrieve repository state and manage local storage paths. These operations are transparent and restricted to the stated purpose of the skill.
[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by processing external data from Git commit messages and file names.
Ingestion points: Output from git status and git log commands.
Boundary markers: Data is interpolated into a structured Markdown list template.
Capability inventory: Directory creation (mkdir) and file-writing capabilities.
Sanitization: No explicit sanitization or escaping of the Git output is implemented, relying on the agent's interpretation of the provided context.

forward-lite