defense-researcher
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a remote URL (https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/defense/defense-researcher/SKILL.md) for its own installation and configuration across different agent platforms. This URL is a resource hosted on the skill author's official GitHub repository.
- [DATA_EXFILTRATION]: The documentation identifies several local filesystem paths for persistent configuration, such as ~/.claude/CLAUDE.md and ~/.cursor/rules/defense-researcher.mdc. These are referenced as standard installation targets for persistent instructions and do not represent unauthorized file access or exfiltration behavior.
- [SAFE]: The skill contains comprehensive safety guidelines, including instructions to decline requests for lethal autonomous weapons and protocols for identifying export-controlled information (ITAR/EAR). The instructions prioritize defensive deterrence and ethical boundaries in research.
Audit Metadata