ruv-swarm

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches and executes the ruv-swarm package from the official npm registry using npx for swarm orchestration tasks.
  • [COMMAND_EXECUTION]: The skill defines a set of commands for the agent to manage swarms, including initializing configurations, spawning agents, and running parallel tasks.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection:
  • Ingestion points: Processes untrusted data through task definition files (--file) and inline JSON payloads (--payload) in SKILL.md and references/commands.md.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the provided templates.
  • Capability inventory: The skill can spawn new agents, execute tasks, and modify swarm topologies.
  • Sanitization: There is no evidence of sanitization or validation of the input data before it is processed by the swarm engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 11:15 AM
Security Audit — agent-trust-hub — ruv-swarm