iot-witness-verify
Warn
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto fetch the package@claude-flow/plugin-iot-cognitum@1.0.0from the npm registry at runtime. - [REMOTE_CODE_EXECUTION]: The package downloaded via
npxis executed within the shell environment. This package originates from a third-party namespace that is not categorized as a trusted organization or well-known service. - [COMMAND_EXECUTION]: The skill invokes the
Bashtool to executenpxand thecognitum-iotCLI tool. - [INDIRECT_PROMPT_INJECTION]: The skill accepts a
DEVICE_IDargument which is interpolated directly into a shell command and uses tool outputs for decision-making and storage, creating a potential surface for injection if inputs are malicious. - Ingestion points: User-provided
DEVICE_IDargument inSKILL.md. - Boundary markers: None present to delimit user input from the command string.
- Capability inventory: Shell command execution via the
Bashtool and persistent storage viamemory_store. - Sanitization: No explicit sanitization or validation of the
DEVICE_IDis performed before interpolation into thenpxcommand string.
Audit Metadata