SKILLEMALL.ai
RU Sign in

FC claw-sos

Install, run, and manage the SOS emergency recovery tool for OpenClaw instances. Use when (1) the bot stops responding on Telegram/Discord and needs diagnosis or recovery, (2) you need to install SOS on a new or existing machine, (3) autofix, rollback, network check, or Telegram test is needed, (4) the user mentions "sos", "recovery", "bot is down", "not responding", or "emergency fix".

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: robertfarkash29-source v6.1.2 MIT-0 5 files · 3 scripts body ≈ 802 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerTelegramDiscordInfrastructuretype 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
34/100
safety, quality, tests
Safety 60%
0
Quality 40%
84
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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.

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.
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 · 18

  • high Dangerous commands cmd-persistence scripts/sos.sh:224
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    if ls ~/Library/LaunchAgents/*openclaw* &>/dev/null 2>&1 || ls /Library/LaunchDaemons/*openclaw* &>/dev/null 2>&1; then
  • high Dangerous commands cmd-persistence scripts/sos.sh:240
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    local plist=$(ls ~/Library/LaunchAgents/*openclaw* /Library/LaunchDaemons/*openclaw* 2>/dev/null | head -1)
  • high Dangerous commands cmd-persistence scripts/sos.sh:244
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$plist" 2>/dev/null || true
  • high Dangerous commands cmd-persistence scripts/sos.sh:257
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$plist" 2>/dev/null || true
Medium and low: 14
  • medium Dangerous commands cmd-pipe-to-shell scripts/install.sh:35
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    echo -e "${YELLOW}Try: INSTALL_DIR=~/.local/bin bash <(curl -fsSL ...)${NC}"
    code literal
  • medium Dangerous commands cmd-privilege scripts/install.sh:50
    Privilege escalation / world-writable permissions
    $SUDO curl -fsSL "$RAW_URL" -o "${INSTALL_DIR}/${SCRIPT_NAME}"
  • medium Dangerous commands cmd-privilege scripts/install.sh:52
    Privilege escalation / world-writable permissions
    $SUDO wget -qO "${INSTALL_DIR}/${SCRIPT_NAME}" "$RAW_URL"
  • medium Dangerous commands cmd-privilege scripts/install.sh:60
    Privilege escalation / world-writable permissions
    $SUDO chmod +x "${INSTALL_DIR}/${SCRIPT_NAME}"
  • medium Dangerous commands cmd-privilege scripts/uninstall.sh:23
    Privilege escalation / world-writable permissions
    $SUDO rm -f "${INSTALL_DIR}/${SCRIPT_NAME}"
  • medium Dangerous commands cmd-pipe-to-shell skill-card.md:25
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    Mitigation: Prefer the bundled script or a pinned, reviewed release and avoid unattended `curl | bash` installs. <br>
    quoted
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:26
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://raw.githubusercontent.com/clawsos/claw-sos/main/install.sh | bash
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/install.sh:5
    Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)
    # Usage: curl -fsSL https://raw.githubusercontent.com/clawsos/claw-sos/main/install.sh | bash
    comment
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/install.sh:6
    Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)
    # Or:    wget -qO- https://raw.githubusercontent.com/clawsos/claw-sos/main/install.sh | bash
    comment
  • low Dangerous commands cmd-background-process scripts/sos.sh:270
    Starts a background / autostarted process
    nohup node "$OC_BIN" gateway --port 18789 &>/dev/null &
  • low Exfiltration exfil-webhook-url scripts/sos.sh:402
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    chat_id=$(timeout 5 curl -sf "https://api.telegram.org/bot${token}/getUpdates?limit=1" 2>/dev/null \
    placeholder
  • low Exfiltration net-credential-use scripts/sos.sh:402
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    chat_id=$(timeout 5 curl -sf "https://api.telegram.org/bot${token}/getUpdates?limit=1" 2>/dev/null \
    vendor-host
  • low Exfiltration exfil-webhook-url scripts/sos.sh:422
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    local result=$(timeout 10 curl -sf -X POST "https://api.telegram.org/bot${token}/sendMessage" \
    placeholder
  • low Exfiltration net-credential-use scripts/sos.sh:422
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    local result=$(timeout 10 curl -sf -X POST "https://api.telegram.org/bot${token}/sendMessage" \
    vendor-host

Files scanned: 5. 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 55/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 3 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 17 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 802 tokens
  • 100Progress reporting. Reports progress

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
  • -212 emoji in the instructions: noise for the model
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 4 example trigger phrases
  • +3Description length 389: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 17 items
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

External checks

ClawHub: suspicious
This appears to be a real OpenClaw emergency recovery tool, but it needs Review because its automatic repair and install paths can make privileged, system-wide changes without enough confirmation.
LLM: suspicious (high) · VirusTotal: · 29 May 2026