se-dev-script

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's setup scripts (Prepare.bat and prepare.sh) fetch the uv package manager from astral.sh and a BusyBox binary from frippery.org. These are well-known development tools required for the skill's operation and are handled as safe infrastructure setup.
  • [COMMAND_EXECUTION]: The skill uses shell commands to manage a local script index and perform searches via specialized Python tools (index_scripts.py, search_scripts.py). This behavior is documented and scoped to the skill's local directory and standard Space Engineers data paths.
  • [PROMPT_INJECTION]: The skill processes Space Engineers C# script source code, which represents an indirect prompt injection surface. Ingestion points: The search_scripts.py and index_scripts.py tools read .cs files from the filesystem and Steam Workshop folders. Boundary markers: No explicit delimiters or isolation instructions are used when returning code snippets to the agent. Capability inventory: The skill includes the Bash tool, allowing for shell command execution. Sanitization: No specific sanitization or filtering is applied to the ingested script content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 01:35 AM
Security Audit — agent-trust-hub — se-dev-script