linkpix-grok-sales
Fail
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: HIGHPERSISTENCEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PERSISTENCE]: The instructions direct the agent to modify the user's shell configuration file (~/.bashrc) to ensure the Node.js path is persisted across sessions.- [EXTERNAL_DOWNLOADS]: The skill fetches Node.js binaries and verification files from the official nodejs.org domain. It also uses well-known mirrors including npmmirror.com and tsinghua.edu.cn for package management.- [DYNAMIC_EXECUTION]: The skill employs dynamic script execution via python -c to perform image resizing and uses npx to run the sharp-cli tool for similar processing tasks.- [COMMAND_EXECUTION]: The skill executes multiple shell commands to set up the environment (curl, tar, sha256sum) and to interact with the qhkit CLI for video generation and status tracking.- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes user-supplied prompts and images to generate video content.
- Ingestion points: User-provided prompts and image file paths in SKILL.md.
- Boundary markers: None identified in the prompt interpolation steps.
- Capability inventory: Subprocess execution of qhkit, python, and npx (all in SKILL.md).
- Sanitization: No explicit sanitization or validation of the input prompt is described before passing it to 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
- AI detected serious security threats
Audit Metadata