The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell scripts located in .agents/scripts/ and ~/.agents/scripts/ based on descriptions found in an index file.
[DYNAMIC_EXECUTION]: The agent is prompted to create new executable scripts and run them immediately to verify functionality, which allows for the creation and execution of arbitrary code at runtime.
[PERSISTENCE]: The skill maintains a global script library in the user's home directory (~/.agents/scripts/), ensuring that saved scripts are available and can be executed in future agent sessions.
[INDIRECT_PROMPT_INJECTION]: The agent relies on external INDEX.md files to identify scripts for execution. If a project repository contains a malicious index or script, the agent may be induced to run unauthorized commands.
Ingestion points: INDEX.md files in project-local and global script directories.
Boundary markers: No delimiters or safety warnings are specified for the content read from these files.
Capability inventory: The agent can write files, modify permissions (executable bit), and execute shell commands.
Sanitization: The instructions do not include steps to sanitize or validate the content of the scripts before they are executed.

reuse-scripts