se2-dev
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill automates the installation of the
graphifyypackage and itsleidenextra from PyPI, which provides thegraspologicclustering backend. These are legitimate tools for the skill's structural analysis functionality. - [COMMAND_EXECUTION]: The
GraphifyPrepareandGraphifyCheckscripts (both .sh and .bat) execute system commands to check for theuvpackage manager, verify available disk space via PowerShell, and manage the execution of the Graphify CLI. - [DYNAMIC_EXECUTION]: The preparation scripts utilize hardcoded Python snippets (
python -c) to probe the environment for specific libraries and to validate the schema and content of generated JSON clustering data. - [INDIRECT_PROMPT_INJECTION]: The skill processes Space Engineers 2 source code and plugin sources to build structural graphs. It explicitly mitigates indirect prompt injection risks by filtering out documentation and metadata files that could trigger LLM-based extraction.
- Ingestion points: Processes C# and IL files within the
Data/DecompiledandData/Sourcesdirectories. - Boundary markers: The
graphify_prepare.shandGraphifyPrepare.batscripts implement extensive exclusion patterns (--exclude *.md,--exclude *.txt,--exclude *.yaml, etc.) to ensure the tool does not process non-code content. - Capability inventory: File system read/write access for graph storage, execution of the
graphifytool, and package installation capabilities. - Sanitization: Strict extension filtering ensures that only source code is processed by the local AST-based extractor, preventing unintended LLM invocations.
Audit Metadata