The Agent Skills Directory

[SAFE]: The skill operates as a legitimate security utility for OT/ICS environments. It facilitates asset visibility and threat detection through standard Nozomi Guardian API integrations.
[COMMAND_EXECUTION]: The scripts/agent.py script utilizes subprocess.run to execute the curl binary for network requests. While it uses the -k (insecure) flag which bypasses SSL certificate validation, the use of a list-based argument structure effectively prevents shell injection vulnerabilities.
[INDIRECT_PROMPT_INJECTION]: The skill presents a vulnerability surface for indirect prompt injection by processing external network alerts and asset metadata. Ingestion points: Network data is ingested via API endpoints such as /api/v1/alerts and /api/v1/nodes. Boundary markers: None are present in the report generation scripts. Capability inventory: The skill has the ability to write JSON reports to the filesystem and execute subprocesses. Sanitization: There is no explicit sanitization of alert descriptions or node labels. The risk is assessed as safe because the script does not interpret or execute instructions from the ingested data.

implementing-ot-network-traffic-analysis-with-nozomi