laravel-plugin-discovery

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill requires the agent to connect to https://laraplugins.io/mcp/plugins to perform searches and retrieve package metrics. This activity involves network operations to a third-party domain not on the predefined allowlist.
  • [PROMPT_INJECTION]: The skill processes untrusted external data such as package READMEs and descriptions, which constitutes an indirect prompt injection surface.
  • Ingestion points: Data is retrieved from the LaraPlugins API via the SearchPluginTool and GetPluginDetailsTool (as defined in SKILL.md).
  • Boundary markers: The skill lacks explicit instructions or delimiters to isolate untrusted external content or warn the agent against executing embedded instructions.
  • Capability inventory: The skill itself does not provide tools for file system modifications or code execution, limiting the impact of potential injections.
  • Sanitization: There are no documented sanitization or validation steps for the data received from the remote MCP server.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 04:01 AM
Security Audit — agent-trust-hub — laravel-plugin-discovery