ralph-tui-create-beads
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external PRD documentation (markdown or text) and incorporates its content into shell commands (
bd create). This creates an attack surface where malicious content within a PRD could attempt to influence the agent's behavior or inject payloads into the task tracking system. - Ingestion points: Processes PRD content from files or text input in SKILL.md.
- Boundary markers: No specific boundary markers or instructions to ignore embedded instructions are provided to the agent for processing the PRD content.
- Capability inventory: The agent is instructed to execute
bd createandbd dep addshell commands as part of the bead creation process. - Sanitization: No explicit sanitization or validation of the PRD content is performed before interpolation into command arguments.
- [COMMAND_EXECUTION]: The skill's primary function involves generating and executing shell commands using the
bdCLI tool to create and manage tasks (beads) and their dependencies. This behavior is documented throughout SKILL.md and is the intended functionality of the skill.
Audit Metadata