kmp-deep-linking
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard implementation templates for cross-platform deep linking including path parsing and route navigation.
- [DATA_EXFILTRATION]: No sensitive data access or unauthorized external network transmission patterns were identified. All URLs used in the code examples and configuration templates are standard placeholders (e.g., example.com).
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads, package installations, or dynamic command execution. Code is purely declarative for navigation logic.
- [PROMPT_INJECTION]: No prompt injection patterns, role-play overrides, or instructions to bypass safety guidelines were detected in the skill metadata or body.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting external URLs (Category 8). However, it implements strong boundary markers and sanitization via regex-based parsing in
DeepLinkParser.ktand restricts capabilities to internal app navigation using the NavController. This significantly mitigates risks of malicious URL input causing unintended actions.
Audit Metadata