skills/mukul975/anthropic-cybersecurity-skills/performing-ot-vulnerability-assessment-with-claroty/Gen Agent Trust Hub
performing-ot-vulnerability-assessment-with-claroty
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the Known Exploited Vulnerabilities (KEV) catalog from CISA's official government domain (cisa.gov). This is a well-known service providing authoritative cybersecurity data.
- [COMMAND_EXECUTION]: The skill provides an agent script (
scripts/agent.py) that performs HTTP requests to a user-specified Claroty xDome instance. The API token and base URL are managed via standard command-line arguments. - [INDIRECT_PROMPT_INJECTION]: The skill processes vulnerability data from external APIs (Claroty) and security feeds (CISA).
- Ingestion points: Data enters the system via the Claroty xDome API and the CISA KEV JSON feed.
- Boundary markers: The script generates text-based reports and JSON output without specific delimiters to separate external data from instructions.
- Capability inventory: The script is limited to network GET requests and file writing for reporting; it does not execute arbitrary code based on the ingested data.
- Sanitization: The skill includes vulnerability titles and descriptions in its output without escaping, which is standard for reporting tools but represents a typical data-processing surface.
Audit Metadata