godot-gdscript-mastery
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides auditing scripts that ingest and process local project files, which presents a surface for indirect prompt injection if those files contain malicious instructions.\n
- Ingestion points: The scripts
scripts/performance_analyzer.gd,scripts/signal_architecture_validator.gd, andscripts/type_checker.gdrecursively scan the Godot project'sres://directory to read and evaluate GDScript files.\n - Boundary markers: The analysis logic does not implement specific boundary markers or instructions to ignore potential instructions embedded in code comments or strings within the scanned files.\n
- Capability inventory: Capabilities are limited to
DirAccessandFileAccessfor reading local project files and printing output to the Godot console. No write access, network operations, or subprocess execution capabilities were found.\n - Sanitization: Ingested content is processed using regular expressions for pattern matching and is not sanitized or escaped before being presented to the agent.
Audit Metadata