SKILLEMALL.ai
GitHub ↗ RU Sign in

FC openclaw-course

(no description)

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: chatgptkrylor v1.0.0 MIT-0 11 files body ≈ 1 176 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureInfrastructureLearningtype 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
F
0/100
safety, quality, tests
Safety 60%
0
Quality 40%
0
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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 · 24

  • high Dangerous commands cmd-pipe-to-shell references/04-CONTEXT-AND-COSTS.md:37
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://ollama.com/install.sh | sh
  • high Dangerous commands cmd-pipe-to-shell references/04-CONTEXT-AND-COSTS.md:51
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://ollama.com/install.sh | sh
Medium and low: 22
  • medium Dangerous commands cmd-pipe-to-shell references/01-FOUNDATIONS.md:98
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://openclaw.ai/install.sh | bash
    vendor-host
  • medium Exfiltration net-credential-use references/01-FOUNDATIONS.md:748
    Credential used in a network call (verify the destination is the intended service)
    curl -H "x-api-key: $ANTHROPIC_API_KEY" \
  • medium Dangerous commands cmd-privilege references/01-FOUNDATIONS.md:757
    Privilege escalation / world-writable permissions
    sudo chown -R $USER:$USER ~/.openclaw
  • medium Dangerous commands cmd-privilege references/01-FOUNDATIONS.md:764
    Privilege escalation / world-writable permissions
    sudo chown -R $(whoami):$(whoami) ~/.openclaw
  • medium Dangerous commands cmd-pipe-to-shell references/01-FOUNDATIONS.md:821
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://openclaw.ai/install.sh | bash
    vendor-host
  • medium Dangerous commands cmd-privilege references/03-LOCAL-POWER.md:425
    Privilege escalation / world-writable permissions
    sudo cp main /usr/local/bin/whisper-cli
  • medium Dangerous commands cmd-privilege references/03-LOCAL-POWER.md:1291
    Privilege escalation / world-writable permissions
    sudo chown -R $(whoami) ~/.openclaw/workspace
  • medium Dangerous commands cmd-pipe-to-shell-known-host references/05-VPS-EMPLOYEE.md:142
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://deb.nodesource.com/setup_22.x | bash -
  • medium Dangerous commands cmd-privilege references/05-VPS-EMPLOYEE.md:508
    Privilege escalation / world-writable permissions
    sudo cp openclaw.service /etc/systemd/system/
  • medium Dangerous commands cmd-privilege references/05-VPS-EMPLOYEE.md:844
    Privilege escalation / world-writable permissions
    sudo tee /etc/logrotate.d/openclaw > /dev/null << 'EOF'
  • medium Dangerous commands cmd-privilege references/05-VPS-EMPLOYEE.md:908
    Privilege escalation / world-writable permissions
    sudo chmod 600 /swapfile
  • medium Exfiltration exfil-read-secret-files references/06-SECURITY.md:122
    Reads credential / secret files (documentation of a security skill)
    ssh-copy-id -i ~/.ssh/id_e…pub openclaw@your-server-ip
    security skill
  • medium Dangerous commands cmd-persistence references/06-SECURITY.md:855
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    ls -la /etc/cron.d/ /etc/cron.hourly/ /etc/cron.daily/ | tee -a "$REPORT_FILE"
    security skill
  • low Dangerous commands cmd-privilege references/01-FOUNDATIONS.md:137
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    appendWindowsPath=false' | sudo tee /etc/wsl.conf
    quoted
  • low Dangerous commands cmd-background-process references/04-CONTEXT-AND-COSTS.md:44
    Starts a background / autostarted process
    sudo systemctl enable ollama
  • low Dangerous commands cmd-background-process references/05-VPS-EMPLOYEE.md:138
    Starts a background / autostarted process
    systemctl enable fail2ban
  • low Secrets in code secret-anthropic-key references/05-VPS-EMPLOYEE.md:424
    Anthropic API key (placeholder value)
    ANTHROPIC_API_KEY=sk-a…xxx
    placeholder
  • low Dangerous commands cmd-background-process references/05-VPS-EMPLOYEE.md:514
    Starts a background / autostarted process
    sudo systemctl enable openclaw
  • low Dangerous commands cmd-cron-mention references/05-VPS-EMPLOYEE.md:668
    Mentions editing / listing crontab
    sudo crontab -e
  • low Dangerous commands cmd-background-process references/06-SECURITY.md:348
    Starts a background / autostarted process (documentation of a security skill)
    systemctl enable fail2ban
    security skill

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 11. 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 59/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 9 mutating operations with no state check
  • 50When it triggers. States when to use, but not when not to
  • 50Failures and branches. 0 branches, has a failure section
  • 100Tools and files. No external tools needed
  • 100Steps. 41 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1176 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +1No license
  • +2Single-language instructions
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 41 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (8 of 8)

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

External checks

ClawHub: suspicious
This appears to be a legitimate OpenClaw course reference, but it needs Review because its helper can read outside its reference folder and the docs include powerful setup commands with incomplete safety framing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026