The Agent Skills Directory

[COMMAND_EXECUTION]: The skill leverages the Bash tool to perform environment checks and generate terminal commands. It instructs the agent to check for the presence of the asciinema utility and provides guidance for installing it via brew install asciinema in the troubleshooting section.
[INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect injection because it ingests untrusted user data and uses it to construct executable shell commands without defined sanitization protocols.
Ingestion points: The skill accepts user-provided values for the file, --title, and --idle-time-limit arguments defined in SKILL.md.
Boundary markers: None. The skill does not provide instructions to the agent to treat these inputs as literal strings or to validate them against malicious shell metacharacters.
Capability inventory: The skill has access to the Bash tool and is explicitly instructed to "Build and display recording command" using these inputs.
Sanitization: Absent. There are no instructions or scripts provided to escape, filter, or validate the user-supplied arguments before they are interpolated into the final shell command.

record