plan-mobile-readiness
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is strictly limited to an 'audit and plan only' scope, explicitly prohibiting the agent from modifying manifests, Data Safety forms, or store listings. This design prevents unauthorized or accidental configuration changes.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project data including Capacitor/React Native manifests and configuration files (ingestion points in SKILL.md). While boundary markers and sanitization are absent, the risk is minimized by a restricted capability inventory that excludes tool usage, file writing, or network operations, maintaining a 'plan-only' workflow.
Audit Metadata