skills/cursor/plugins/swarm/Gen Agent Trust Hub

swarm

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to orchestrate and spawn multiple parallel subagents using parameters like subagent_type: generalPurpose and environment: "cloud". This is a standard platform capability for task delegation.
  • [DATA_EXPOSURE]: The skill references a local configuration file located at ~/.cursor/rules/pstack-models.mdc to retrieve model preferences. This is used for legitimate configuration purposes within the assistant's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 02:21 PM
Security Audit — agent-trust-hub — swarm