se2-dev-plugin

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The preparation scripts (Prepare.bat and prepare.sh) download the uv package manager from Astral's official site (astral.sh) and the busybox.exe utility from its primary Windows port site (frippery.org). These are standard tools for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill makes extensive use of command-line tools including git for repository management and uv for Python environment execution. The Python scripts (git_utils.py, download_plugin_source.py) use the subprocess module to invoke these commands with controlled arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it downloads C# source code from external GitHub repositories into the Data/Sources/ directory. This content is then indexed and intended to be read by the AI agent. Maliciously crafted comments or documentation within those external plugins could attempt to influence the agent's behavior.
  • Ingestion points: External C# source files and repository metadata downloaded to Data/Sources/ by download_plugin_source.py.
  • Boundary markers: None identified; the agent reads raw file contents through standard shell utilities.
  • Capability inventory: The agent has access to Bash commands, dotnet build for compilation, and uv run for executing Python scripts.
  • Sanitization: No explicit sanitization or instruction-filtering is applied to the content of the downloaded source code before the agent processes it.
  • [DYNAMIC_EXECUTION]: The skill uses the tree-sitter library to parse and index C# code at runtime. It also provides guidance for dotnet build operations to compile the developed plugins.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 02:22 PM