The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute git log. The command is scoped to repository history analysis and does not involve arbitrary execution or external network connectivity.
[DATA_EXPOSURE]: The skill accesses project-specific data within the production/ directory, including YAML and Markdown files. No attempts to access sensitive system paths (e.g., SSH keys, AWS configs) or environment variables were identified.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its reliance on external data sources for report generation. \n
Ingestion points: Reads content from production/sprints/, production/milestones/, and production/sprint-status.yaml. \n
Boundary markers: None; the skill processes ingested content directly into analysis phases without explicit delimiters. \n
Capability inventory: Includes Write, Bash, and AskUserQuestion tools. \n
Sanitization: No explicit validation or filtering of ingested data is described before it is used to influence agent behavior or command arguments.

retrospective