igniteui-wc-generate-from-image-design
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill's primary function involves processing user-provided design images, which represents a surface for indirect prompt injection. An attacker could potentially embed malicious instructions within a design mockup to influence the agent's code generation or installation behavior.\n
- Ingestion points: User-provided design images (screenshots, mockups, or wireframes) as described in Step 1 of SKILL.md.\n
- Boundary markers: None identified; the agent is instructed to analyze and decompose the image content directly without specific delimiters or isolation rules.\n
- Capability inventory: The agent is authorized to perform package installations (SKILL.md Step 6) and project file modifications (SKILL.md Step 7).\n
- Sanitization: No specific validation or sanitization process for the content extracted from the images is mentioned.\n- [EXTERNAL_DOWNLOADS]: The skill identifies and manages the installation of official Ignite UI library packages, such as
igniteui-webcomponentsandigniteui-grid-lite, which are required to implement the discovered UI components.\n- [NO_CODE]: The skill is composed entirely of Markdown instructions and reference files, containing no bundled scripts, binaries, or other executable code.
Audit Metadata