flow-nexus-swarm

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install and use the flow-nexus package from the official registry. This is a vendor-owned resource associated with the author 'ruvnet' and is required for the skill's operation.
  • [COMMAND_EXECUTION]: Provides instructions for using the flow-nexus CLI and MCP server. These commands are used for account management and starting the MCP service to enable the skill's orchestration features.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted data which presents a surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context via the task parameter in mcp__flow-nexus__task_orchestrate and the input_data field in mcp__flow-nexus__workflow_execute.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the task or workflow definitions.
  • Capability inventory: The skill orchestrates agents capable of performing web searches, generating and implementing code, and managing files through the execution stream features.
  • Sanitization: There is no evidence of input validation or sanitization of the data processed within the workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 05:43 AM