skills/mukul975/anthropic-cybersecurity-skills/performing-scada-hmi-security-assessment/Gen Agent Trust Hub
performing-scada-hmi-security-assessment
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data sources including network packet captures (PCAP) and JSON configuration files, creating an attack surface for indirect prompt injection. * Ingestion points: Data is ingested from PCAP files via the pyshark library and from HMI configuration files via json.loads in scripts/agent.py. * Boundary markers: Absent; there are no specific delimiters or instructions to ignore content within processed files. * Capability inventory: The agent has capabilities for network communication (socket scanning and HTTP requests via urllib.request) and local file system writes for report generation. * Sanitization: Absent; data extracted from external files is processed and included in assessment reports without explicit validation or escaping.
Audit Metadata