godot-analyst
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze external Godot project files (scripts, scenes, and assets), which constitutes an indirect prompt injection attack surface.
- Ingestion points: The analytical engine reads directory structures, script source code through
scoring_logic.gd, and resource import metadata across the project'sres://tree. - Boundary markers: The instructions lack clear delimiters or safety warnings to ignore potentially malicious instructions embedded in comments or strings within the analyzed project files.
- Capability inventory: The agent is instructed to execute a suite of scoring scripts (Python and GDScript) and maintains persistent state via the
visionary_comparison.gdscript, which writes to the localuser://data directory. - Sanitization: The skill does not appear to sanitize or filter the content of analyzed files before processing them with RegEx or incorporating them into its architectural reports.
Audit Metadata