deep-linking
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides code for ingesting and parsing external URI data (Deep Links and Universal Links) to facilitate application navigation. While this represents an entry point for untrusted data, the provided logic is strictly limited to internal routing (e.g., navigating to product or profile screens) and does not involve risky capabilities such as command execution or sensitive file access.
- [COMMAND_EXECUTION]: The documentation includes command-line examples using
adbandxcrun simctlfor local testing on mobile simulators and devices. These are standard developer tools and do not pose a security risk to the agent or the host environment. - [REMOTE_CODE_EXECUTION]: The skill mentions external services and SDKs such as Firebase Dynamic Links, Branch, AppsFlyer, and the Google Play Install Referrer library. These references are for legitimate mobile attribution and deep linking purposes, and the installation pattern for the Google Play library is standard practice.
Audit Metadata