Scan Report
5 /100
sense-memory
Sovereign persistence for AI agents — encrypted key-value memories and journal entries on Nostr relays
The sense-memory skill is a legitimate Nostr-based encrypted memory store. It declares pip as a required binary, relies on published PyPI packages, and has no hidden functionality, obfuscation, or credential exfiltration.
Safe to install
Approve for use. The skill is straightforward and well-documented.
Findings 1 items
| Severity | Finding | Location |
|---|---|---|
| Low | External package dependency not bundled Supply Chain | metadata.json:20 |
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | NONE | NONE | — | No file read/write in skill files |
| Network | NONE | READ | ✓ Aligned | External PyPI packages (nostrkey, sense_memory) — Nostr relay connections docume… |
| Shell | NONE | NONE | — | pip declared in metadata.openclaw.requires.bins, used only for package install |
| Environment | NONE | READ | ✓ Aligned | NOSTRKEY_PASSPHRASE, NOSTR_NSEC read by external packages (documented as require… |
4 findings
Medium External URL 外部 URL
https://clawhub.ai/vveerrgg/nostrkey SKILL.md:36 Medium External URL 外部 URL
https://clawhub.ai/vveerrgg/nostr-profile SKILL.md:288 Medium External URL 外部 URL
https://clawhub.ai/vveerrgg/nse SKILL.md:291 Medium External URL 外部 URL
https://huje.tools metadata.json:8 File Tree
3 files · 16.8 KB · 402 lines Markdown 1f · 303L
JSON 1f · 53L
Python 1f · 46L
├─
▾
examples
│ └─
basic_usage.py
Python
├─
metadata.json
JSON
└─
SKILL.md
Markdown
Dependencies 2 items
| Package | Version | Source | Known Vulns | Notes |
|---|---|---|---|---|
nostrkey | >=0.1.1 | pip | No | Min version pinned, not exact version |
sense-memory | latest | pip | No | Version not specified — pulls latest |
Security Positives
✓ SKILL.md clearly documents all behavior including encryption (NIP-44), storage modes (NIP-78, NIP-04), and network targets (relays)
✓ No base64, obfuscated code, or anti-analysis patterns detected
✓ No credential harvesting or data exfiltration — secrets remain local for encryption only
✓ No hidden instructions or prompt injection detected
✓ Input validation documented (key sanitization, content length caps, relay query caps)
✓ No direct shell execution or subprocess usage in skill files
✓ Memory keys validated against path traversal patterns
✓ MIT license declared