prototype
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided project briefs and existing code, which represents an attack surface for indirect prompt injection. 1. Ingestion points: Project briefs and existing project files are read as context (SKILL.md). 2. Boundary markers: Instructions require explicit labeling of real, simulated, and deferred components. 3. Capability inventory: The skill generates, runs, and inspects code artifacts. 4. Sanitization: While no specific input sanitization is mentioned, the skill mandates isolating fixture data from live systems.
- [DYNAMIC_EXECUTION]: The skill involves the generation and execution of code artifacts to create runnable prototypes. Evidence: The core instruction is to produce a runnable artifact and inspect it (SKILL.md).
- [SAFE]: The skill demonstrates a security-conscious design by instructing the agent to disable outbound calls in prototypes to prevent data leakage and warning that UI role-switches do not constitute authorization.
Audit Metadata