qinghu-image-deai-hd
Fail
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides instructions to download and install Node.js from the official distribution site (nodejs.org) and its official mirrors. The installation process correctly includes a checksum verification step using
sha256sumto ensure file integrity before extraction. As these sources are well-known services, this is documented as standard environment setup. - [PERSISTENCE]: Instructions in the skill suggest appending the Node.js installation path to the shell profile (e.g.,
~/.bashrc) to maintain access across sessions. While this involves modifying persistence configuration files, it is a routine step for manual software installation and path configuration. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process outputs from the
qhkitCLI tool, such as error messages and status updates, which are then presented to the user. This creates a potential surface where external tool data enters the agent's context. - Ingestion points: Command-line output from
qhkit workflow statusandqhkit workflow estimatedescribed inSKILL.md. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: Execution of subprocesses via the
qhkitcommand. - Sanitization: No specific sanitization or filtering of the tool's stdout/stderr is required before the agent relays the message.
Recommendations
- HIGH: Downloads and executes remote code from: https://nodejs.org/dist/v22.22.3/SHASUMS256.txt - DO NOT USE without thorough review
Audit Metadata