flow-nexus-swarm

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the flow-nexus package from the NPM registry and references external documentation and platform resources at flow-nexus.ruv.io and github.com/ruvnet/flow-nexus.- [COMMAND_EXECUTION]: The setup instructions include executing shell commands such as npm install -g flow-nexus@latest and npx flow-nexus@latest login to configure the environment and authenticate with the platform.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8):
  • Ingestion points: Untrusted data enters the agent context via the task parameter in the mcp__flow-nexus__task_orchestrate tool and the input_data parameter in mcp__flow-nexus__workflow_execute.
  • Boundary markers: The skill documentation does not provide delimiters or instructions to ignore embedded commands within the provided usage examples.
  • Capability inventory: The skill possesses extensive capabilities for orchestrating tasks, spawning specialized agents, and managing complex multi-step workflows across a swarm.
  • Sanitization: There is no mention of input validation or sanitization for data processed by the workflow orchestration tools.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 02:11 PM