The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git log and git diff commands to retrieve project history and statistics for report generation as described in the Data Collection step.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from git log (commit messages) and the PROGRESS.md file.
Ingestion points: Reads task history and project status from PROGRESS.md and commit messages from git log.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified in the instructions for processing this external data.
Capability inventory: The skill has the ability to write to the filesystem (creating/updating PROGRESS.md and generating report files) and execute shell commands via the git tool.
Sanitization: There is no mention of sanitization or validation for the content ingested from the repository's history or local files.

progress-brief