infographic-item-creator
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (HIGH): The skill processes content from 'references/item-prompt.md' and existing files in 'src/designs/items' to generate code, creating an attack surface where malicious instructions in these files can influence the output.
- Ingestion points: Local file reads from 'references/item-prompt.md' and directory scanning of 'src/designs/items'.
- Boundary markers: Absent. There are no instructions to help the agent distinguish between data and instructions in the read files.
- Capability inventory: The skill allows the agent to generate and update .tsx and .ts files in the repository.
- Sanitization: No sanitization or validation of the input data is performed before it is used to construct the generated TypeScript code.
Recommendations
- AI detected serious security threats
Audit Metadata