skills/beel-collab/presets.dev/aspire/Gen Agent Trust Hub

aspire

Fail

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions for installing the Aspire CLI via a shell script piped to bash (curl -sSL https://aspire.dev/install.sh | bash) or PowerShell (irm https://aspire.dev/install.ps1 | iex). These commands target the official domain for the Microsoft-managed project.
  • [EXTERNAL_DOWNLOADS]: Fetches installation scripts, project templates, and integration documentation from official domains including aspire.dev and Microsoft-affiliated GitHub organizations.
  • [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by design, as it enables the agent to fetch and process external content from documentation repositories and API registries.
  • Ingestion points: Documentation search and retrieval tools (search_docs, get_doc, get_integration_docs) and Context7 fallback services.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified in the guidance.
  • Capability inventory: The skill interacts with the aspire CLI, which manages the local resource lifecycle, including starting/stopping containers and executables, and configuring environment variables.
  • Sanitization: There is no evidence of sanitization or content validation for the retrieved external documentation data.
Recommendations
  • HIGH: Downloads and executes remote code from: https://aspire.dev/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Apr 14, 2026, 07:29 AM
Security Audit — agent-trust-hub — aspire