qinghu-background-swap

Fail

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: HIGHPERSISTENCEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PERSISTENCE]: The skill includes instructions to modify the user's shell profile (~/.bashrc) by appending an export command that adds the local Node.js binary directory to the system PATH. This ensures that the environment configuration and the installed tools remain available across future terminal sessions.
  • [EXTERNAL_DOWNLOADS]: The skill fetches Node.js binaries and checksum verification files directly from nodejs.org and utilizes npmmirror.com as a fallback service. These external resources are used to bootstrap the execution environment required for the background replacement functionality.
  • [COMMAND_EXECUTION]: The skill executes multiple shell-based tools, including the npm package manager for installing the @iqinghu/qhkit package and the qhkit CLI itself to perform image generation, configuration, and environment self-checks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user which is interpolated into the execution of shell commands.
    1. Ingestion points: User-supplied text for the prompt field and image file paths for uploadedImages (SKILL.md).
    2. Boundary markers: The skill documentation recommends using the @params.json file-based parameter passing method, which acts as a boundary to prevent shell-level command injection.
    3. Capability inventory: The skill environment allows for subprocess execution of qhkit, npm, curl, sha256sum, and tar (SKILL.md).
    4. Sanitization: No explicit sanitization or filtering of the prompt content is performed before it is embedded into the JSON payload used by the CLI tool.
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
Risk Level
HIGH
Analyzed
Sep 21, 2026, 04:09 PM