tech-article-image
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs its stated function of generating image prompts based on user input. It follows a structured workflow to analyze themes and does not exhibit any signs of malicious intent, obfuscation, or unauthorized access to sensitive system resources.
- [PROMPT_INJECTION]: The skill processes untrusted technical articles provided by users to extract visual themes. This creates a surface for indirect prompt injection where an attacker could embed instructions in an article to influence the output prompt or image tool parameters.
- Ingestion points: Technical articles and user-provided descriptions.
- Boundary markers: Uses a structured prompt construction template.
- Capability inventory: Interfaces with image generation tools (e.g.,
mcp-image:generate_image). - Sanitization: No explicit filtering of input content is performed, but the impact is restricted to visual output generation.
- [EXTERNAL_DOWNLOADS]: The skill's installation process fetches the configuration file from a public repository on GitHub. This is a standard and transparent distribution method for agent skills.
Audit Metadata