laravel-plugin-discovery
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection where untrusted content from package READMEs or descriptions could influence agent behavior.
- Ingestion points: External data enters through GetPluginDetailsTool and SearchPluginTool from SKILL.md.
- Boundary markers: No delimiters or instructions are used to wrap external content or warn the agent to ignore embedded commands.
- Capability inventory: The skill retrieves external content which could be used to exploit broader agent capabilities like file system access or shell execution.
- Sanitization: No validation or sanitization of README content is described.
- [EXTERNAL_DOWNLOADS]: Connects to the LaraPlugins.io MCP server (https://laraplugins.io/mcp/plugins) to retrieve package metadata. This is a primary function of the skill and uses a domain associated with the service.
Audit Metadata