SKILLEMALL.ai
GitHub ↗ RU Sign in

FC openclaw

(no description)

Not recommendedcritical or high security findings · low grade F
thedotmack/claude-mem Agent Skills author: thedotmack Apache-2.0 13 files · 7 scripts body ≈ 3 942 tokens Open the sourcegithub.com↗ analyzed 2 d ago

This guide walks through setting up the claude-mem plugin on an OpenClaw gateway.

As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationSlackDiscordTelegramWhatsAppAI and agentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
F
0/100
safety, quality, tests
Safety 60%
0
Quality 40%
0
Run on models
none yet
Process rating
C
52/100
Has gaps
Result and completion w 14
0
When it triggers w 12
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Add a description to the frontmatter: without it the skill never triggers.
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 · 17

  • high Dangerous commands cmd-pipe-to-shell SKILL.md:10
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://install.cmem.ai/openclaw.sh | bash
  • high Dangerous commands cmd-pipe-to-shell SKILL.md:20
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://install.cmem.ai/openclaw.sh | bash -s -- --provider=gemini --api-key=YOUR_KEY
  • high Dangerous commands cmd-pipe-to-shell SKILL.md:26
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://install.cmem.ai/openclaw.sh | bash -s -- --non-interactive
  • high Dangerous commands cmd-pipe-to-shell SKILL.md:32
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://install.cmem.ai/openclaw.sh | bash -s -- --upgrade
Medium and low: 13
  • medium Dangerous commands cmd-pipe-to-shell-known-host install.sh:419
    Pipe-to-shell installer from a well-known host (still executes remote code)
    if ! curl -fsSL https://bun.sh/install | bash; then
  • medium Dangerous commands cmd-pipe-to-shell-known-host install.sh:479
    Pipe-to-shell installer from a well-known host (still executes remote code)
    if ! curl -LsSf https://astral.sh/uv/install.sh | sh; then
  • medium Dangerous commands cmd-pipe-to-shell install.sh:1491
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    echo "  bash <(curl -fsSL https://install.cmem.ai/openclaw.sh)"
    code literal
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:58
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://bun.sh/install | bash
  • medium Exfiltration net-credential-use src/index.ts:478
    Credential used in a network call (verify the destination is the intended service)
    const response = await fetch(`https://api.telegram.org/bot${botToken}/sendMessage`, {
  • low Dangerous commands cmd-pipe-to-shell-known-host install.sh:422
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    error "  curl -fsSL https://bun.sh/install | bash"
    code literal
  • low Dangerous commands cmd-pipe-to-shell-known-host install.sh:482
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    error "  curl -LsSf https://astral.sh/uv/install.sh | sh"
    code literal
  • low Exfiltration exfil-webhook-url src/index.ts:478
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    const response = await fetch(`https://api.telegram.org/bot${botToken}/sendMessage`, {
    placeholder
  • low Dangerous commands cmd-pipe-to-shell test-install.sh:1572
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed; test fixture / example file)
    echo "=== curl | bash usage comment ==="
    detectorcode literalfixture
  • low Dangerous commands cmd-pipe-to-shell test-install.sh:1574
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed; test fixture / example file)
    if grep -q 'curl -fsSL.*raw.githubusercontent.com.*install.sh | bash' "$INSTALL_SCRIPT"; then
    detectorcode literalfixture
  • low Dangerous commands cmd-pipe-to-shell test-install.sh:1575
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; test fixture / example file)
    test_pass "install.sh contains curl | bash usage comment"
    code literalfixture
  • low Dangerous commands cmd-pipe-to-shell test-install.sh:1577
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; test fixture / example file)
    test_fail "install.sh should contain curl | bash usage comment"
    code literalfixture
  • low Dangerous commands cmd-pipe-to-shell test-install.sh:2029
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed; test fixture / example file)
    if grep -q 'curl -fsSL.*raw.githubusercontent.com.*install.sh | bash' "$skill_file"; then
    detectorcode literalfixture

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error frontmatter SKILL.md: no YAML frontmatter block found
  • error name-missing SKILL.md: frontmatter has no `name`
  • error description-missing SKILL.md: no `description` — the skill can never trigger

Process rating: all ten parameters 52/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 85Steps. 28 steps, 3 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3942 tokens
  • 100Running it twice. Mutating operations check current state

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 0: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Structure: 34 headings
  • +3Step-by-step instructions: 28 items
  • +4Has examples (29 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.

In the sandbox The scripts kept to themselves

The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

Запущено 7 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

Из них 2 не дошли до работы, и об их поведении мы ничего не узнали.

e2e-verify.shзавершился с кодом 133
install.shне запустился: ✗ Fix the issue above and re-run the installer.
test-e2e.shне запустился: test-e2e.sh: line 13: docker: command not found
test-install.shзавершился с кодом 133
test-sse-consumer.jsничего за пределами своей папки
src/index.test.tsничего за пределами своей папки
src/index.tsничего за пределами своей папки

19 Oct 2026