gns3-node-operations
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted input such as project IDs, node names, and template names that are interpolated into GNS3 API requests. Ingestion points: User inputs for project_id, node_id, name, and template parameters in the tools defined in SKILL.md. Boundary markers: None present in the instructions to delimit user-provided strings or instruct the agent to ignore embedded commands. Capability inventory: The skill allows for the creation, starting, stopping, and reloading of network nodes via the mcp-servers/gns3-mcp-server/gns3_mcp_server.py script. Sanitization: No sanitization or validation logic is documented in the skill instructions, relying entirely on the server-side implementation.
Audit Metadata