dual-coding-designer
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill does not contain any scripts, executables, or third-party dependencies, posing no risk of remote code execution or system compromise.
- [SAFE]: No sensitive information, such as API keys or credentials, is hardcoded or accessed by the skill.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) by interpolating untrusted user input directly into the instruction prompt.
- Ingestion points: The prompt in
SKILL.mdprocesses external data via variables such as{{verbal_content}},{{student_profiles}}, and{{existing_visuals}}. - Boundary markers: No explicit delimiters (e.g., XML tags or clear separators) or 'ignore embedded instructions' warnings are used to isolate untrusted data from the system instructions.
- Capability inventory: The skill is limited to text-based visual design recommendations and does not possess capabilities for file manipulation, network access, or command execution.
- Sanitization: No sanitization or validation of the input content is performed before interpolation.
Audit Metadata