The Agent Skills Directory

[COMMAND_EXECUTION]: Executes a local helper script at ~/.claude/scripts/org-standards.sh to collect repository status. The skill also references a /setup-scripts command to regenerate this script if it is missing or not executable.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external repositories to automate code changes and Pull Request generation across a GitHub organization.
Ingestion points: The agent is instructed in SKILL.md to read CLAUDE.md, .github/workflows/, and various project configuration files from target repositories.
Boundary markers: No boundary markers or instructions to isolate external content are present to prevent embedded instructions in target repositories from influencing agent behavior.
Capability inventory: The skill utilizes powerful capabilities including file system writes, git worktree/branch management, and Pull Request creation via the gh CLI.
Sanitization: There is no evidence of sanitization or validation of the data retrieved from repositories before it is incorporated into reports or automated changes.
[PROMPT_INJECTION]: Contains a control directive ('IMPORTANT: If this command is being run as a standalone request, automatically exit...') intended to modify the agent's default operational lifecycle upon completion of the task.

org-standards