p-image
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts which are interpolated into shell commands executed via the
beltCLI tool. - Ingestion points: The
promptvalue within the JSON input passed tobelt app runcommands inSKILL.md. - Boundary markers: The instructions do not define delimiters or specific markers to isolate the user-provided prompt from the command structure.
- Capability inventory: The skill leverages the
Bashtool to execute system-level commands through thebeltCLI. - Sanitization: No explicit sanitization or escaping mechanisms are described for handling the user-provided prompt content before it is processed by the CLI tool.
Audit Metadata