threat-modeling-ics
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from Microsoft TMT exports (.csv) and model files (.tm7). This creates an attack surface for indirect prompt injection, where malicious instructions embedded in threat descriptions or justifications could attempt to influence the agent's behavior during analysis. \n
- Ingestion points: Reads content from local CSV and TM7 files provided in the workspace. \n
- Boundary markers: Absent; the instructions do not explicitly direct the agent to ignore or delimit instructions found within the input data. \n
- Capability inventory: The agent has the capability to read and write local files (CSV, Markdown) and perform complex reasoning on architecture. \n
- Sanitization: Absent; the skill relies on direct processing of textual data for classification and scoring. \n- [EXTERNAL_DOWNLOADS]: The skill references documentation and calculators from well-known services and trusted organizations, including Microsoft (Azure/Learn), MITRE (ATT&CK/CWE), FIRST (CVSS), and BSI (Risk Prioritization). These references are for documentation purposes and do not involve automated downloads or execution of remote scripts.
Audit Metadata