despia-v3-extensions

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a developer guide and template repository for Despia V3 extensions. Analysis of the provided documentation and native code (Swift and Java) confirms that the implementation follows security best practices.
  • Secure Network Handling: The sample code for both iOS and Android platforms includes explicit URL validation (isApprovedURL and strict URL parsing) to ensure that recorded data is only sent to pre-approved hosts defined in the extension manifest.
  • Least Privilege: The native code requests standard permissions necessary for its stated function (audio recording, background processing) and documents the requirement for user consent via the platform's permission systems.
  • No Obfuscation: The code is provided in clear text with detailed comments explaining the logic. There are no signs of hidden instructions, malicious obfuscation, or encoded payloads.
  • Build Integrity: The instructions emphasize that all dependencies must be pinned and that the platform (Despia) performs an approval process for all native files, mitigating supply chain risks.
  • No Dynamic Injection: No use of dynamic context injection or shell command placeholders was detected in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 03:15 AM