AGENT LAB: SKILLS
skills/github/awesome-copilot/aspire/Gen Agent Trust Hub

aspire

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION] (CRITICAL): Multiple files including SKILL.md and references/cli-reference.md instruct the user to execute curl -sSL https://aspire.dev/install.sh | bash. This pattern is a high-risk remote code execution vector that bypasses script verification.
  • [COMMAND_EXECUTION] (HIGH): The skill recommends using irm https://aspire.dev/install.ps1 | iex for Windows installation in references/cli-reference.md and references/deployment.md. This is an unsafe practice equivalent to piped bash execution.
  • [EXTERNAL_DOWNLOADS] (LOW): The skill references several external resources and documentation sites (e.g., aspire.dev, github.com/dotnet/aspire). While these are official sources, the automated instructions for direct execution increase the risk profile.
  • [PROMPT_INJECTION] (LOW): The skill possesses a surface for indirect prompt injection via the ingestion of documentation and logs.
  • Ingestion points: The search_docs and list_console_logs tools provided by the MCP server (references/mcp-server.md).
  • Boundary markers: None identified; external data is not explicitly delimited from agent instructions.
  • Capability inventory: Powerful CLI commands like aspire deploy and aspire publish (references/cli-reference.md).
  • Sanitization: No evidence of input sanitization for data fetched via MCP tools.
Recommendations
  • HIGH: Downloads and executes remote code from: https://aspire.dev/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 05:40 PM