appbuilder-ui-scaffolder
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read existing project files in the web-src/src/ directory to understand current conventions before generating new code. This behavior establishes a surface for indirect prompt injection, where an adversary who has modified local project files could embed instructions that manipulate the agent's output or tool usage.
- Ingestion points: User project files located in the web-src/src/ directory, accessed via the Read tool.
- Boundary markers: The skill does not define specific delimiters or warnings to ignore embedded instructions within these files.
- Capability inventory: The skill is authorized to use Bash (npm, node, npx), Read, Write, and Edit tools, which could be leveraged if an injection occurs.
- Sanitization: There are no explicit instructions to sanitize or validate the content of the read files before they are used to influence code generation.
Audit Metadata