discover-plugins

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform a simple directory listing (ls plugins/), which is used to verify currently installed components for the user.
  • [EXTERNAL_DOWNLOADS]: The instructions explain how to add the ruvnet/ruflo marketplace and install plugins from the vendor's own repository. These references are associated with the skill's author and represent standard functionality.
  • [PROMPT_INJECTION]: The skill facilitates discovery by ingesting and processing metadata from a plugin marketplace based on user search queries, which presents an indirect injection surface.
  • Ingestion points: Data enters the agent's context via the results of mcp__claude-flow__transfer_plugin-search and mcp__claude-flow__transfer_plugin-info tools as described in SKILL.md.
  • Boundary markers: The skill does not employ explicit delimiters to isolate external metadata from system instructions.
  • Capability inventory: The skill has access to Bash and Read tools.
  • Sanitization: No explicit validation or filtering of the retrieved plugin descriptions is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:22 PM
Security Audit — agent-trust-hub — discover-plugins