source-command-gsd-workstreams
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
gsd-sdkcommand-line utility to perform lifecycle operations on parallel workstreams, such as listing, creating, and switching states. - [INDIRECT_PROMPT_INJECTION]: The skill instructions allow for the interpolation of user-provided input (the
<name>argument) directly into shell command templates (e.g.,gsd-sdk query workstream.create <name>). This presents a vulnerability surface for command injection if the input contains shell metacharacters. - Ingestion points: User-supplied
<name>parameter for subcommands inSKILL.md. - Boundary markers: No delimiters or ignore-instructions are specified for the user input.
- Capability inventory: Shell command execution via
gsd-sdkthroughoutSKILL.md. - Sanitization: The skill lacks instructions for the agent to sanitize, validate, or escape the
<name>argument before execution.
Audit Metadata