The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs active network operations to identify vulnerabilities in industrial control systems.
The scripts/agent.py script uses the socket library to conduct TCP port scans on a user-provided target IP to identify open SCADA protocols (e.g., Modbus, S7comm).
The scripts/agent.py script uses urllib.request to perform HTTP Basic Authentication attempts against the target using a list of common default credentials to identify insecure configurations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources during a security audit.
Ingestion points: The skill reads local HMI configuration JSON files (via --config) and network traffic captures (via --pcap) using pyshark in scripts/agent.py.
Boundary markers: No specific delimiters or instructions are used to prevent the agent from following directions that might be embedded in the analyzed data.
Capability inventory: The script has the ability to perform network requests, conduct port scans, and write report files to the local file system.
Sanitization: The tool relies on standard JSON parsing and the pyshark library for data extraction without additional sanitization layers for potentially malicious payloads in traffic captures.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of external Python libraries to function.
It references pyshark and requests as dependencies. These are well-known and standard libraries within the cybersecurity and networking community used for their intended purposes.

performing-scada-hmi-security-assessment