laravel-plugin-discovery

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires connection to a third-party MCP server at https://laraplugins.io/mcp/plugins to fetch plugin data.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted package descriptions and README content from an external source, creating an injection surface. 1. Ingestion points: Search result summaries and detailed readme content retrieved via the SearchPluginTool and GetPluginDetailsTool. 2. Boundary markers: The instructions lack explicit delimitation or directives to ignore instructions embedded within the retrieved package data. 3. Capability inventory: The agent uses the external data to evaluate package health and provide recommendations to the user. 4. Sanitization: No content validation or sanitization mechanisms are described for the data fetched from the external API.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 02:58 PM