The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash(git:*) tool to execute git log commands. This is used to retrieve commit history for the daily review. The execution is restricted to the git binary.
[DYNAMIC_EXECUTION]: The skill implements a hooks system where it checks for the existence of .groove/hooks/start.md and is instructed to 'execute each item' found in the ## Actions section. This allows the agent's behavior to be modified at runtime based on the contents of a local file.
[INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to instructions embedded in local configuration files.
Ingestion points: The skill reads instructions from .groove/hooks/start.md and configuration parameters from .groove/index.md.
Boundary markers: Absent. The skill does not use delimiters or instructions to ignore potential injections within the hook file.
Capability inventory: The skill possesses Read, Write, Edit, and Bash(git:*) capabilities, which can be leveraged by instructions found in the hook file.
Sanitization: Absent. There is no validation or filtering of the actions defined in the hook file before execution.

groove-daily-start