The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several local shell commands including git log, git show, git status, git diff, git config, and date to gather commit metadata and repository state. These operations are restricted to the local environment to facilitate the work-logging functionality.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks. Ingestion points: Untrusted data enters the agent context via git log and git show commands in SKILL.md, which retrieve commit messages and diffs. Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are employed to separate the ingested commit content from the skill's operational logic. Capability inventory: The skill utilizes subprocess calls to the git and date binaries. Sanitization: No evidence of escaping or filtering of external commit content was found before the data is processed into the final markdown list.

work-log-writer