The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to generate and execute shell commands using the allowed Bash tool, including examples for complex system tasks like database backups and file system searches.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from terminal output and error logs, creating a potential vector for instructions embedded in command results to influence the agent.
Ingestion points: Terminal command output and error messages processed by the agent in SKILL.md and references/implementation.md.
Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded in the terminal data.
Capability inventory: The skill has access to the Bash tool for command execution and Read for file system access.
Sanitization: No sanitization or validation of the processed terminal output is specified.
[PERSISTENCE]: The documentation in references/directory-structure.md identifies shell configuration files (.bashrc, .zshrc) as targets for terminal integration, which is a common persistence mechanism for maintaining access across shell sessions.

windsurf-terminal-ai