pre-submission-audit

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a static analysis and checklist tool for mobile app metadata and source code. No malicious patterns such as credential harvesting, unauthorized data exfiltration, or persistence mechanisms were found.
  • [PROMPT_INJECTION]: The skill processes untrusted external data (app code and metadata) which is an inherent part of its primary function. While this is a surface for indirect prompt injection, it is mitigated by the skill's specific purpose of providing a structured audit report.
  • Ingestion points: Mobile application source code, configuration files (e.g., PrivacyInfo.xcprivacy), and store metadata.
  • Boundary markers: Absent; the skill directly processes the provided application context.
  • Capability inventory: The skill refers to specific developer tools (e.g., privacy-manifest-rn, accessibility-audit) and generates status reports. It does not perform arbitrary code execution or outbound network requests.
  • Sanitization: None explicitly defined within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 11:17 PM
Security Audit — agent-trust-hub — pre-submission-audit