swarm-advanced
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes MCP tools to orchestrate and execute shell commands such as npm run test and search publications across multiple agents as part of its core functionality.
- [EXTERNAL_DOWNLOADS]: The documentation instructs users to install the claude-flow framework from the NPM registry and run it using npx.
- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data during research tasks, creating a surface for indirect prompt injection.
- Ingestion points: Data entering via web-search, academic-search, and content-extraction capabilities in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the examples.
- Capability inventory: The skill can execute shell commands, spawn agents, and manage memory across the workflow.
- Sanitization: There are no visible filters or validation steps for content retrieved from external sources.
Audit Metadata