swarm-advanced

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation and use of the claude-flow framework from the npm registry using npm install -g claude-flow@alpha.
  • [COMMAND_EXECUTION]: Orchestration workflows involve the execution of CLI commands such as npx claude-flow and the parallel running of local build or test scripts (e.g., npm run test) as part of development and testing patterns.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is identified because the skill's primary function is to ingest and process data from untrusted external sources, such as web and academic searches, which are then used to drive agent actions.
  • Ingestion points: The mcp__claude-flow__parallel_execute tool is utilized in references/patterns.md to gather external content from web searches and academic databases.
  • Boundary markers: The provided examples do not demonstrate the use of delimiters or instructions intended to isolate external content from the agent's core instructions.
  • Capability inventory: The skill utilizes tools capable of executing shell commands in references/patterns.md and writing to the local filesystem via mcp__claude-flow__memory_backup.
  • Sanitization: No explicit logic for the validation or sanitization of ingested search results is present in the provided reference materials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 06:40 AM
Security Audit — agent-trust-hub — swarm-advanced