WorldThreatModelHarness

Persistent world model system across 11 time horizons (6mo→50yr) for adversarial analysis of ideas, strategies, and investments. USE WHEN threat model, world mo

84/100

Security score

The WorldThreatModelHarness skill was audited on Mar 1, 2026 and we found 4 security issues across 3 threat categories. Review the findings below before installing.

Categories Tested

Security Issues

medium line 79

Curl to non-GitHub URL

SourceSKILL.md

79	curl -s -X POST http://localhost:8888/notify \

medium line 42

Access to hidden dotfiles in home directory

SourceSKILL.md

42	Models are stored at: `~/.claude/MEMORY/RESEARCH/WorldModels/`

medium line 87

Access to hidden dotfiles in home directory

SourceSKILL.md

87	`~/.claude/skills/PAI/USER/SKILLCUSTOMIZATIONS/WorldThreatModelHarness/`

low line 79

External URL reference

SourceSKILL.md

79	curl -s -X POST http://localhost:8888/notify \

Scanned on Mar 1, 2026

View Security Dashboard