widgetkit-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill content consists of legitimate technical documentation and best practices for Apple's WidgetKit framework. No evidence of malicious intent, prompt injection, or suspicious data exfiltration was found across the skill instructions or reference files.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code, which represents a vulnerability surface for indirect prompt injection. However, the operational impact is minimal as the skill instructions are highly specific to technical artifacts (e.g., TimelineProvider, Widget protocol) and the agent is constrained by a structured reporting protocol (Hard Gates). Ingestion Point: User-provided source code (SKILL.md). Boundary Markers: Absent. Capability Inventory: Reading code and generating textual reviews. Sanitization: Absent.
Audit Metadata