mikrotik-routeros-rsc

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process external RouterOS script files (.rsc), creating a surface where malicious instructions could be hidden in comments or strings to influence agent behavior.
  • Ingestion points: The agent reads user-provided .rsc files and processes them via the scripts/lint_rsc.py tool.
  • Boundary markers: No specific delimiters or safety warnings are present in the instructions to prevent the agent from following instructions embedded within the analyzed scripts.
  • Capability inventory: The agent can execute the provided Python linter, generate/modify network configuration scripts, and provide technical advice on RouterOS management.
  • Sanitization: Neither the skill instructions nor the Python linter sanitize the content of the .rsc files to strip potential prompt injection payloads before the agent reviews them.
  • [Command Execution] (SAFE): The skill includes a local utility script scripts/lint_rsc.py. Technical review of this script confirms it is a benign static analysis tool.
  • The script uses only standard Python libraries (re, sys, pathlib).
  • It performs read-only operations on the target file and does not use dangerous functions like eval(), exec(), or subprocess to handle file content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:19 PM