Scan Report
5 /100
neural-memory
Persistent memory for AI agents — stores experiences as interconnected neurons, recalls through spreading activation
Pure documentation skill package containing only SKILL.md files for NeuralMemory operations with no executable code, no sensitive file access, and no dangerous capabilities declared.
Safe to install
This skill is safe to use. The three sub-skills (memory-audit, memory-evolution, memory-intake) are well-documented workflow guides that only use custom NeuralMemory tools (nmem_*) with no shell, filesystem, or network access required.
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | NONE | NONE | — | No filesystem access declared; ~/.neuralmemory/config.toml referenced only as co… |
| Network | NONE | NONE | — | No network access tools declared; external URLs are documentation links only |
| Shell | NONE | NONE | — | No shell execution declared or implied |
| Environment | NONE | NONE | — | No environment variable access declared |
| Skill Invoke | READ | READ | ✓ Aligned | Uses nmem_* tools only via NeuralMemory MCP server |
| Clipboard | NONE | NONE | — | No clipboard access declared |
| Browser | NONE | NONE | — | No browser access declared |
| Database | NONE | NONE | — | NeuralMemory internal graph database not exposed to skill |
2 findings
Medium External URL 外部 URL
https://nhadaututtheky.github.io/neural-memory SKILL.md:40 Medium External URL 外部 URL
https://marketplace.visualstudio.com/items?itemName=neuralmem.neuralmemory SKILL.md:41 File Tree
8 files · 31.4 KB · 935 lines Markdown 5f · 838L
JSON 3f · 97L
├─
▾
hooks
│ └─
hooks.json
JSON
├─
▾
skills
│ ├─
▾
memory-audit
│ │ └─
SKILL.md
Markdown
│ ├─
▾
memory-evolution
│ │ └─
SKILL.md
Markdown
│ ├─
▾
memory-intake
│ │ └─
SKILL.md
Markdown
│ └─
README.md
Markdown
├─
marketplace.json
JSON
├─
plugin.json
JSON
└─
SKILL.md
Markdown
Security Positives
✓ No executable code - all files are pure documentation/metadata
✓ No shell, filesystem, or network access tools declared
✓ All allowed tools (nmem_*) are custom NeuralMemory operations that must be provided by an MCP server
✓ No credential harvesting, data exfiltration, or remote code execution patterns
✓ Skills use structured memory types and provide clear audit/pruning/creation workflows
✓ No base64, no eval(), no curl|bash, no subprocess patterns
✓ Context file (~/.neuralmemory/config.toml) is read-only reference, not access target
✓ MIT licensed with transparent repository references