bindings-synchronization

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Command Execution]: The skill directs the AI agent to execute local build and generation tools, specifically python3 tools/apigen/generate_android.py -j and go run . within the tools/beamsplitter directory. These commands are used to maintain synchronization across the project's language bindings and are consistent with the skill's primary purpose.
  • [Indirect Prompt Injection Surface]: The skill involves processing public header files to identify API changes. This presents a theoretical surface for indirect prompt injection where instructions could be embedded in source code comments or metadata.
  • Ingestion points: Public C++ headers located in filament/include/filament/ (SKILL.md).
  • Boundary markers: None specified within the skill itself; relies on the agent's native content processing boundaries.
  • Capability inventory: The skill utilizes shell command execution via Python and Go to run local project scripts (SKILL.md).
  • Sanitization: No explicit sanitization or filtering of source code content is described in the synchronization guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 06:50 PM
Security Audit — agent-trust-hub — bindings-synchronization