The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute shell commands for creating temporary files, interfacing with system clipboard managers (pbcopy, xclip, xsel), and performing file cleanup.
[INDIRECT_PROMPT_INJECTION]: The skill processes session history and final responses, which are untrusted data sources that could contain malicious instructions designed to influence agent behavior during the formatting phase.
Ingestion points: The session's final answer/response identified during the workflow (SKILL.md).
Boundary markers: None explicitly defined in the prompt instructions to delimit untrusted data from the instructions.
Capability inventory: The skill possesses file write capabilities and the ability to execute system commands via the Bash tool.
Sanitization: The skill employs a quoted heredoc (<< 'EOF') when writing to the temporary file, which is a robust security measure that prevents the shell from performing variable expansion or command substitution on the data being written.

md-copy