SKILLEMALL.ai
RU Sign in

BC rag-memory

Vector memory search and RAG skill for OpenClaw. Provides vector_search tool backed by Qdrant, auto-syncs memory .md files and Postgres records via nomic-embed-text embeddings. Triggers on "search memory", "vector search", "resync memory", "RAG", "qdrant".

ClawHub Agent Skills author: Morten Bojer v1.1.1 MIT-0 15 files · 2 scripts body ≈ 1 739 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedurePostgreSQLAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
79/100
safety, quality, tests
Safety 60%
72
Quality 40%
90
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 12

    ✓ No critical or high findings

    Medium and low: 12
    • medium Dangerous commands cmd-privilege SKILL.md:101
      Privilege escalation / world-writable permissions
      | sudo tee /etc/systemd/system/sysclaw-rag-{sync,watch}.service > /dev/null
    • medium Dangerous commands cmd-privilege SKILL.md:102
      Privilege escalation / world-writable permissions
      sudo cp ~/.openclaw/skills/rag-memory/systemd/sysclaw-rag-sync.timer /etc/systemd/system/
    • medium Dangerous commands cmd-privilege SKILL.md:103
      Privilege escalation / world-writable permissions
      sudo cp ~/.openclaw/skills/rag-memory/systemd/sysclaw-rag-watch.path /etc/systemd/system/
    • medium Exfiltration net-redirectable-api-key sync_to_qdrant.py:54
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • low Secrets in code secret-high-entropy-token plugin/package-lock.json:46
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…3wH+jfWB…yfN+lFri…oov+PzfnxxD5g==",
      detector
    • low Secrets in code secret-high-entropy-token plugin/package-lock.json:137
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…wIN//F77/IADDSs58i+MDaO…jeo+YFg==",
      detector
    • low Secrets in code secret-high-entropy-token plugin/package-lock.json:735
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…8tJ++Ku97…8Zu+xfBP…2pf+8SGN5/NoytfKgYPIw==",
      detector
    • low Secrets in code secret-high-entropy-token plugin/package-lock.json:815
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…x9D+4jKA…w7A==",
      detector
    • low Secrets in code secret-high-entropy-token plugin/package-lock.json:829
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…rQc+GZ14…I4P/jsSo…7rC/hms+WclQQ==",
      detector
    • low Dangerous commands cmd-privilege references/config-paths.example.md:14
      Privilege escalation / world-writable permissions (detector / deny-list definition; documentation table row; test fixture / example file)
      | `~/.openclaw/skills/rag-memory/systemd/` | Systemd unit source copies — edit here, then `sudo cp` to deploy |
      detectortablefixture
    • low Dangerous commands cmd-privilege SKILL.md:41
      Privilege escalation / world-writable permissions (detector / deny-list definition; documentation table row)
      | `systemd/` | Source-of-truth copies of systemd units (deploy with `sudo cp` + `daemon-reload`) |
      detectortable
    • low Dangerous commands cmd-background-process systemd/deploy.sh:23
      Starts a background / autostarted process
      systemctl enable --now sysclaw-rag-sync.timer sysclaw-rag-watch.path

    Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 60/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 4 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
    • 100Steps. 29 steps
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1739 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 13 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -33 of 3 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 4 example trigger phrases
    • +3Description length 256: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 29 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

    External checks

    ClawHub: suspicious
    This is a real RAG memory skill, but it defaults to sending ordinary prompts and stored memory content to configured embedding and vector services with limited runtime visibility.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026