defold-native-extension-editing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill contains technical documentation and code examples for developing game engine extensions, using standard C++ and JavaScript entry points for the Defold engine.
  • [EXTERNAL_DOWNLOADS]: The skill references configuration files (e.g., .clang-format) and example repositories located on GitHub under the official Defold and indiesoftby organizations. These are recognized as trusted or well-known sources within this development context.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the editing of source code files, which creates an attack surface for indirect prompt injection if those files contain malicious instructions.
  • Ingestion points: Source code files (.c, .cpp, .js) and manifests (.manifest) provided by the user.
  • Boundary markers: None defined to isolate the agent from instructions embedded in code comments or data.
  • Capability inventory: The agent has file system read/write access and shell execution capabilities to manage the extension development process.
  • Sanitization: No specific filtering or validation mechanisms are provided for the code content being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:23 PM
Security Audit — agent-trust-hub — defold-native-extension-editing