The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a shell script located at ~/.claude/scripts/org-deps.sh with arguments provided by the user. It also describes a workflow for applying fixes that involves running git commands to create worktrees, update files, run tests, and create pull requests.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, specifically NEWS.md files and git commit messages from repositories within the specified organization to detect breaking changes.
Ingestion points: Git commit logs and NEWS.md files from audited repositories.
Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are defined for the ingested text.
Capability inventory: The agent has capabilities to execute shell scripts, modify files (version constraints), and perform network operations via git and pull request tools.
Sanitization: No sanitization or validation of the ingested content is specified.
[PROMPT_INJECTION]: The skill includes instructions ("IMPORTANT: If this command is being run as a standalone request, automatically exit...") that attempt to influence the agent's control flow and termination behavior based on the execution context.

org-deps