skills/mukul975/anthropic-cybersecurity-skills/hunting-advanced-persistent-threats/Gen Agent Trust Hub
hunting-advanced-persistent-threats
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill instructions and associated scripts are focused on legitimate cybersecurity research and threat detection activities.
- [EXTERNAL_DOWNLOADS]: The script agent.py is configured to download public threat intelligence data from MITRE's official STIX/TAXII repositories using the attackcti library.
- [COMMAND_EXECUTION]: The documentation provides examples of Velociraptor VQL, osquery SQL, and Splunk SPL queries. These are intended for user-guided hunting and are not executed autonomously by the skill's code.
- [DATA_EXFILTRATION]: The script allows users to output hunt reports to a JSON file. The output location is determined by a user-provided CLI argument, and no sensitive system data is accessed or transmitted.
Audit Metadata