aspireify

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Installation of Official Tooling]: The skill provides instructions for installing the Aspire CLI using a shell pipe command (curl -sSL https://aspire.dev/install.sh | bash). While executing remote scripts from the internet is a general security consideration, this specific URL targets the official installation endpoint for .NET Aspire, a well-known technology platform. Contextually, this is a necessary prerequisite for the skill's orchestration capabilities.
  • [Processing Repository Content]: The skill involves scanning local repository files, including environment variables, configuration files, and source code, to scaffold a resource graph. The ingestion of untrusted data from the local environment introduces a surface for indirect prompt injection, where malicious instructions hidden in the code could influence agent behavior. The skill incorporates several mitigation strategies:
  • Ingestion points: Repository scanning tools like find, cat, and grep are used to inventory project files and connection strings (SKILL.md, references/scan-and-propose.md).
  • Boundary markers: The agent is explicitly instructed to present a proposed resource graph and integration list for user confirmation before performing any edits (Workflow Phase 2).
  • Capability inventory: The skill uses file-writing capabilities to modify Program.cs and apphost.ts and executes the aspire CLI for validation.
  • Sanitization: Validation steps include running aspire describe to sanity-check the resulting graph after edits are applied.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 03:54 PM
Security Audit — agent-trust-hub — aspireify