init
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs and executes shell commands using the pipecat CLI (pipecat-ai-cli) to scaffold new projects based on user configuration.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (such as project names and configuration choices) and interpolates them directly into a shell command.
- Ingestion points: User responses during the configuration flow in SKILL.md.
- Boundary markers: No explicit instruction to treat inputs as untrusted data or use delimiters.
- Capability inventory: Executes the pipecat init command via shell.
- Sanitization: The instructions do not explicitly require sanitization of user-supplied arguments before execution.
Audit Metadata