se-dev-mod
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill indexes and reads external C# source code from third-party Space Engineers mods. These files represent an untrusted data surface where an attacker could embed malicious instructions (e.g., in code comments) to influence the AI agent's behavior during search or analysis tasks. \n
- Ingestion points: The cs_indexer.py script reads the content of .cs files from mod directories. \n
- Boundary markers: Code snippets are presented to the agent without explicit boundary markers or safety instructions. \n
- Capability inventory: The skill allows the execution of a defined set of bash commands through BusyBox and Python scripts via uv. \n
- Sanitization: No sanitization is performed on the source code content before it is displayed to the agent. \n- [EXTERNAL_DOWNLOADS]: The skill's setup scripts (Prepare.bat and prepare.sh) download the uv package manager and the busybox.exe utility from the official domains astral.sh and frippery.org. These downloads are required to provision the development environment and are fetched from well-known service providers.
Audit Metadata