The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute gsd-tools for various workstream management operations, including listing, creating, and switching workstreams. These operations are performed using the vendor's gsd-tools utility.
[INDIRECT_PROMPT_INJECTION]: The skill interpolates user-provided input, such as the workstream <name>, directly into shell commands (e.g., gsd-tools query workstream.create <name>). This creates a surface for potential command injection if the input is not properly sanitized.
Ingestion points: User-supplied <name> argument in subcommands like create, status, switch, complete, and resume (found in SKILL.md).
Boundary markers: No explicit sanitization or boundary markers are defined in the instructions to delimit the interpolated user input.
Capability inventory: The skill has access to the Bash tool and the gsd-tools command-line utility.
Sanitization: The instructions do not specify any validation, escaping, or filtering for the <name> parameter before it is passed to the shell command.

gsd-workstreams