skills/jcoger/skills/mobile-motion/Gen Agent Trust Hub

mobile-motion

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes structured 'MOTION SPEC' and 'BEAT SHEET' blocks to generate code, which creates a surface for indirect prompt injection. Ingestion points: Specifications and code blocks are ingested via the agent's prompt context. Boundary markers: The instructions do not specify explicit delimiters or markers to isolate potentially malicious instructions within the specs. Capability inventory: The skill allows for the generation and review of React Native and SwiftUI code. Sanitization: The skill relies on manual gate-checks (K1-K8) performed by the agent rather than automated sanitization of input data. \n- [EXTERNAL_DOWNLOADS]: The skill and its reference files direct the user to employ several well-known third-party libraries for mobile development, including react-native-reanimated, react-native-gesture-handler, react-native-worklets, @shopify/react-native-skia, expo-router, expo-haptics, and @gorhom/bottom-sheet. \n- [SAFE]: The skill is a legitimate development tool. No evidence of malicious obfuscation, credential theft, unauthorized network activity, or persistence mechanisms was found. The use of __DEV__ gates and logging in the MotionTuner.tsx utility is consistent with standard developer debugging tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 02:06 AM