dotnet-reverse

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several GitHub repositories for essential .NET reverse engineering tools including dnSpyEx, de4dot, ILSpy, and Detect It Easy. It also suggests third-party MCP (Model Context Protocol) servers for integrating dnSpy with AI agents. These references are standard for the security analysis use case and point to well-known community resources.
  • [COMMAND_EXECUTION]: The documentation provides numerous examples of shell commands for binary analysis, such as using file, strings, powershell for assembly inspection, and CLI tools like de4dot and ilspycmd. These are intended for use by the agent within a controlled reverse engineering environment.
  • [REMOTE_CODE_EXECUTION]: While the skill discusses running scripts (e.g., using dotnet script with dnlib), these are presented as localized analytical tools for the user or agent to perform specific tasks like batch string decryption during a reverse engineering engagement.
  • [DATA_EXFILTRATION]: No patterns associated with unauthorized data exfiltration or credential harvesting were identified. The network-related tools listed in allowed-tools (WebFetch, WebSearch) are consistent with the need to research malware signatures or download deobfuscation signatures.
  • [PROMPT_INJECTION]: The skill does not contain instructions that attempt to bypass safety filters or override the agent's core behavioral guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 08:15 AM
Security Audit — agent-trust-hub — dotnet-reverse