memory-lancedb-pro

github.com/clawhub.ai/memory-lancedb-pro-skill-main
Verdict: Do not install
11 critical0 high1 medium
F
SCORE 0 / 100
$skillox install memory-lancedb-proSoon
Sign in to followFollowing emails you when a re-scan drops the grade. Opt-out is per-creator on /account/billing.

Why grade F?

score · 0 / 100

The current grade reflects 11 critical findings (any 2+ CRITs → F).

11 CRIT0 HIGH1 MED0 LOW
To reach a higher grade
  • D
    Reach Dtarget score 30

    Resolve 10 of your 11 CRIT findings — any single CRIT still keeps you at D.

  • C
    Reach Ctarget score 55

    Resolve all 11 CRIT findings.

  • B
    Reach Btarget score 75

    Resolve all 11 CRIT.

  • A
    Reach Atarget score 95

    Resolve all 11 CRIT.

Thresholds are documented at /docs/grading. Source-of-truth is the grade() function in @skillox/scanner.

Latest scan findings

Scan crawl-gbrrcc4wma3g5ruz7q4rpa7u · Thu, 28 May 2026 16:20:55 GMT · 6ms

crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 175CWE-200
▾
173 "extractMaxChars": 8000,
174 "llm": {
175 "apiKey": "${OPENAI_API_KEY}",← references ${OPENAI_API_KEY} — potential credential leak
176 "model": "gpt-4o-mini",
177 "baseURL": "https://api.openai.com/v1"
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 216CWE-200
▾
214 "extractMaxChars": 8000,
215 "llm": {
216 "apiKey": "${OPENAI_API_KEY}",← references ${OPENAI_API_KEY} — potential credential leak
217 "model": "gpt-4o-mini",
218 "baseURL": "https://api.openai.com/v1"
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 242CWE-200
▾
240{
241 "embedding": {
242 "apiKey": "${OPENAI_API_KEY}",← references ${OPENAI_API_KEY} — potential credential leak
243 "model": "text-embedding-3-small",
244 "baseURL": "https://api.openai.com/v1"
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 253CWE-200
▾
251 "extractMaxChars": 8000,
252 "llm": {
253 "apiKey": "${OPENAI_API_KEY}",← references ${OPENAI_API_KEY} — potential credential leak
254 "model": "gpt-4o-mini",
255 "baseURL": "https://api.openai.com/v1"
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 694CWE-200
▾
6921. **Gateway restart required after any change**: After installing, enabling, disabling, updating, or changing config in `openclaw.json`, you MUST run `openclaw gateway restart` — changes are NOT hot-reloaded.
6932. **Workspace plugins are DISABLED by default**: After git clone, you MUST add `plugins.allow: ["memory-lancedb-pro"]` AND `plugins.entries.memory-lancedb-pro.enabled: true` — without these the plugin silently does not load.
6943. **Env vars in gateway process**: `${OPENAI_API_KEY}` requires env vars set in the *OpenClaw Gateway service* process—not just your shell.← references ${OPENAI_API_KEY} — potential credential leak
6954. **Absolute vs. relative paths**: For existing deployments, always use absolute paths in `plugins.load.paths`.
6965. **`baseURL` not `baseUrl`**: The embedding (and llm) config field is `baseURL` (capital URL), NOT `baseUrl`. Using the wrong casing causes a schema validation error: "must NOT have additional properties". Also note the required `/v1` suffix: `http://localhost:11434/v1`, not `http://localhost:11434`. Do not confuse with `agents.defaults.memorySearch.remote.baseUrl` which uses a different casing.
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 750CWE-200
▾
748| `memory-lancedb-pro: plugin not found` / plugin silently not loading | `plugins.allow` missing (git-clone install) or `enabled: false` | Add `plugins.allow: ["memory-lancedb-pro"]` and set `enabled: true`, then restart |
749| `Unknown plugin id` validation error | Plugin referenced in `entries`/`slots` before it's discoverable | Install/register the plugin first, then add config references |
750| `${OPENAI_API_KEY}` not expanding / auth errors despite env var set | Env var not set in the **gateway process** environment | Set the env var in the service that runs OpenClaw gateway, not just your shell |← references ${OPENAI_API_KEY} — potential credential leak
751| Hooks (`before_agent_start`, `agent_end`) not firing | Gateway not restarted after install/config change | Run `openclaw gateway restart` |
752| Embedding errors with Ollama | Wrong `baseURL` format | Must be `http://localhost:11434/v1` (with `/v1`), field must be `baseURL` not `baseUrl` |
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 766CWE-200
▾
764 "embedding": {
765 "provider": "openai-compatible",
766 "apiKey": "${OPENAI_API_KEY}",← references ${OPENAI_API_KEY} — potential credential leak
767 "model": "text-embedding-3-small"
768 },
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 803CWE-200
▾
801 "enableManagementTools": false,
802 "llm": {
803 "apiKey": "${OPENAI_API_KEY}",← references ${OPENAI_API_KEY} — potential credential leak
804 "model": "gpt-4o-mini",
805 "baseURL": "https://api.openai.com/v1"
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 855CWE-200
▾
853 "smartExtraction": true,
854 "llm": {
855 "apiKey": "${OPENAI_API_KEY}",← references ${OPENAI_API_KEY} — potential credential leak
856 "model": "gpt-4o-mini",
857 "baseURL": "https://api.openai.com/v1"
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 1177CWE-200
▾
1175 "extractMaxChars": 8000,
1176 "llm": {
1177 "apiKey": "${OPENAI_API_KEY}",← references ${OPENAI_API_KEY} — potential credential leak
1178 "model": "gpt-4o-mini"
1179 }
crit
Skill references secret env var ${OPENAI_API_KEY}
The skill instructions reference `${OPENAI_API_KEY}`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 1186CWE-200
▾
1184```json
1185{
1186 "embedding": { "apiKey": "${OPENAI_API_KEY}", "model": "text-embedding-3-small" },← references ${OPENAI_API_KEY} — potential credential leak
1187 "smartExtraction": true
1188}
med
No capability manifest declared
The skill ships without a `manifest.yaml` or `capabilities` block in its frontmatter. Without a manifest, the runtime cannot enforce what this skill is permitted to do.
rule: no-manifest
▾
View latest scan →
skillox.io/c/memory-lancedb-pro