The Agent Skills Directory

[PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it is designed to ingest and analyze untrusted external source code.
Ingestion points: Uses Read, Grep, and Glob tools to ingest contents of .cs, .csproj, and .sln files.
Boundary markers: Absent; the skill does not provide instructions to the agent to treat ingested file content as potentially adversarial.
Capability inventory: The agent's allowed tools are limited to file reading and Model Context Protocol (MCP) documentation retrieval; it lacks permissions for file-writing, network access, or shell execution.
Sanitization: No sanitization or filtering of ingested file content is defined.
[COMMAND_EXECUTION] (SAFE): While the documentation mentions various dotnet CLI commands, the allowed-tools manifest does not grant the agent any tool for executing shell commands, effectively mitigating the risk of unauthorized system modification.
[DATA_EXFILTRATION] (SAFE): No network-capable tools, hardcoded credentials, or access patterns targeting sensitive system files (e.g., SSH keys, credentials) were detected.

moai-lang-csharp