chromadb-memory
Verdict safe, but 1 finding (1 medium), mainly command injection. Most recent scan 2026-02-05.
This skill presents LOW to MEDIUM security risk. It's primarily a plugin extension for OpenClaw that integrates ChromaDB and Ollama for semantic memory. The main concern is a command injection risk in the installation instructions where unsanitized curl output is piped to Python. The skill itself appears to be a legitimate memory enhancement tool with local-only dependencies (no cloud APIs), but the package is incomplete - documentation references TypeScript files that aren't included. Missing manifest metadata (license, allowed-tools, compatibility) reduces transparency. The auto-recall feature could impact performance but isn't a direct security threat. Overall, this appears to be a work-in-progress or incorrectly packaged skill rather than a malicious one, but the command injection risk in setup instructions should be addressed.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Long-term memory via ChromaDB with local Ollama embeddings. Auto-recall injects relevant context every turn. No cloud APIs required — fully self-hosted.
- Package
- 4 files, 14 KB
- SKILL.md
- 398 words, 12+ sections
- Code
- TypeScript (1)
- Version
- 1.0.0
SKILL.md covers: ChromaDB Memory · What It Does · Prerequisites · Install · 1. Copy the plugin extension · 2. Get your collection ID · 3. Add to your OpenClaw config (~/.openclaw/openclaw.json): · 4. Restart the gateway · Config Options · How It Works · Token Cost · Tuning
Findings
MEDIUM Command Injection Risk in Collection ID Retrieval Command Injectionllm
The installation instructions include a shell command that pipes curl output directly to Python without validation. The command 'curl -s http://localhost:8100/api/v2/tenants/default_tenant/databases/default_database/collections | python3 -c "import json,sys; [print(f'{c["id"]} {c["name"]}') for c in json.load(sys.stdin)]"' could be exploited if an attacker controls the ChromaDB server response. Malicious JSON could potentially cause unexpected behavior or information disclosure through crafted collection names.
SKILL.md
curl -s http://localhost:8100/api/v2/tenants/default_tenant/databases/default_database/collections | python3 -c "import json,sys; [print(f'{c["id"]} {c["name"]}') for c in json.load(sys.stdin)]"What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 3.7 KB |
manifest.json | config | 462 B |
scripts/index.ts | script | 8.3 KB |
scripts/openclaw.plugin.json | config | 1.5 KB |
External hosts referenced
github.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/chromadb-memory
- Raw scan result: chromadb-memory-scan.json
- Badge for your README:
- Request a re-scan