skse-plugin-authoring

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch the CommonLibSSE-NG library from a community GitHub repository (alandtse/CommonLibVR) and references Address Library files on Nexus Mods. These are standard resources for SKSE development.\n- [COMMAND_EXECUTION]: The instructions guide the agent to perform shell operations for toolchain setup and project building, specifically utilizing CMake and xmake to compile C++ source code into native DLLs.\n- [DYNAMIC_EXECUTION]: The skill provides patterns for memory patching and vtable manipulation using CommonLibSSE-NG primitives like safe_write and write_vfunc, involving the runtime modification of executable memory within the game process.\n- [INDIRECT_PROMPT_INJECTION]: The plugin-dissection.md guide directs the agent to read and analyze untrusted external SKSE plugin source code, which could contain malicious instructions designed to override agent behavior.\n
  • Ingestion points: Analyzing external C++ source code files during the plugin dissection flow.\n
  • Boundary markers: No specific delimiters or safety instructions are provided to separate analyzed code from the agent's operational context.\n
  • Capability inventory: The agent is instructed to compile C++ code, execute build commands, and manage the file system.\n
  • Sanitization: No sanitization or validation of the audited source code is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 12:45 AM