routeros-container
Warn
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The REST API documentation section provides a TypeScript code snippet that hardcodes a default credential string ('admin:') and demonstrates insecure Basic authentication over a potential HTTP connection.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by demonstrating how to ingest and process data from external RouterOS REST API endpoints without implementing sanitization or boundary markers.\n
- Ingestion points: API responses from '/container' and '/system/resource' in SKILL.md.\n
- Boundary markers: None used in the provided TypeScript examples to isolate data from agent instructions.\n
- Capability inventory: The skill outlines REST API usage for privileged operations like container deletion and creation in SKILL.md.\n
- Sanitization: The provided examples do not include logic for filtering or validating data received from the router.\n- [COMMAND_EXECUTION]: The skill documents the use of powerful RouterOS management commands, including system mode updates, package management, and network configuration, which grant significant control over the host device.
Audit Metadata