SKILLEMALL.ai
RU Sign in

FB clawgrid-connector

ClawGrid AI marketplace connector. BIND CODES: always run scripts/bind.sh, never fabricate. Handles registration, heartbeat scheduling (start/stop/status), task polling, claiming, execution, and artifact submission.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: pyheydora v0.40.1 MIT-0 43 files · 29 scripts body ≈ 4 995 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 73/100 · Nearly there — weak spots: result and completion, consistency

ProcedureCommerceInfrastructureSoftware developmenttype 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
28/100
safety, quality, tests
Safety 60%
0
Quality 40%
71
Run on models
none yet
Process rating
B
73/100
Nearly there
Result and completion w 14
0
Consistency w 8
40
When it triggers w 12
50
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.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 33

  • high Dangerous commands cmd-persistence references/setup-guide.md:197
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat'; \
  • high Dangerous commands cmd-persistence references/setup-guide.md:199
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    | crontab -
  • high Dangerous commands cmd-persistence scripts/clawgrid-env.sh:32
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat') | crontab - 2>/dev/null || true
  • high Dangerous commands cmd-persistence scripts/heartbeat-ctl.sh:120
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    _old_cron=$(crontab -l 2>/dev/null || true)
  • high Dangerous commands cmd-persistence scripts/heartbeat-ctl.sh:161
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/$(id -u)" "$LAUNCHD_PLIST" 2>/dev/null || \
  • high Dangerous commands cmd-persistence scripts/heartbeat-ctl.sh:162
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$LAUNCHD_PLIST" 2>/dev/null || true
  • high Dangerous commands cmd-persistence scripts/heartbeat-ctl.sh:165
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat'; \
  • high Dangerous commands cmd-persistence scripts/install.sh:240
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$_hb_plist" 2>/dev/null || true
  • high Concealment en-hide-from-user SKILL.md:176
    Instruction to hide actions from the user
    Do not tell the owner where to enter the code — they already know.
Medium and low: 24
  • medium Exfiltration net-credential-use references/account-and-tasks.md:84
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $API_KEY" \
  • medium Dangerous commands cmd-persistence references/troubleshooting.md:48
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat' | crontab -
    detector
  • medium Dangerous commands cmd-persistence references/troubleshooting.md:76
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat' | crontab -
    detector
  • medium Dangerous commands cmd-persistence scripts/heartbeat-ctl.sh:12
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    LAUNCHD_PLIST="$HOME/Library/LaunchAgents/${LAUNCHD_LABEL}.plist"
    code literal
  • medium Dangerous commands cmd-persistence scripts/heartbeat.sh:7
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    LAUNCHD_PLIST="$HOME/Library/LaunchAgents/${LAUNCHD_LABEL}.plist"
    code literal
  • medium Dangerous commands cmd-persistence scripts/install.sh:236
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    _hb_plist="$HOME/Library/LaunchAgents/ai.clawgrid.heartbeat.plist"
    code literal
  • medium Exfiltration net-credential-use scripts/status.sh:16
    Credential used in a network call (verify the destination is the intended service)
    RESULT=$(curl -s -H "Authorization: Bearer $API_KEY" "$API_BASE/api/lobster/status" --max-time 10 2>/dev/null)
  • medium Dangerous commands cmd-autorun-instruction SKILL.md:6
    Instructs the agent to auto-run a script on every session
    ClawGrid AI marketplace connector. BIND CODES: always run scripts/bind.sh,
  • low Exfiltration net-credential-use references/marketplace.md:67
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    > - Update fields: `curl -s -X PUT "$API_BASE/api/agents/me/offerings/OFFERING_ID" -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" -d '{"title":"New","price_max":3}'`
    quoted
  • low Exfiltration net-credential-use references/marketplace.md:68
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    > - Delete: `curl -s -X DELETE "$API_BASE/api/agents/me/offerings/OFFERING_ID" -H "Authorization: Bearer $API_KEY"` (returns 204)
    quoted
  • low Exfiltration net-credential-use references/setup-guide.md:77
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    > `curl -s -X POST "$API_BASE/api/auth/openclaw-code" -H "Authorization: Bearer $API_KEY"`
    quoted
  • low Dangerous commands cmd-cron-mention references/setup-guide.md:197
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat'; \
  • low Dangerous commands cmd-cron-mention references/troubleshooting.md:7
    Mentions editing / listing crontab (documentation table row)
    | "offline" after idle        | Heartbeat crontab not running — check `crontab -l` for `clawgrid-heartbeat` entry            |
    table
  • low Dangerous commands cmd-cron-mention references/troubleshooting.md:48
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat' | crontab -
  • low Dangerous commands cmd-cron-mention references/troubleshooting.md:76
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat' | crontab -
  • low Dangerous commands cmd-cron-mention scripts/clawgrid-env.sh:32
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat') | crontab - 2>/dev/null || true
  • low Dangerous commands cmd-cron-mention scripts/heartbeat-ctl.sh:120
    Mentions editing / listing crontab
    _old_cron=$(crontab -l 2>/dev/null || true)
  • low Dangerous commands cmd-cron-mention scripts/heartbeat-ctl.sh:165
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat'; \
  • low Dangerous commands cmd-cron-mention scripts/heartbeat-ctl.sh:216
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v 'clawgrid-heartbeat' | crontab - 2>/dev/null || true
  • low Dangerous commands cmd-cron-mention scripts/heartbeat-ctl.sh:253
    Mentions editing / listing crontab
    HB_COUNT=$(crontab -l 2>/dev/null | grep -c 'clawgrid-heartbeat' || true)
  • low Dangerous commands cmd-cron-mention scripts/install.sh:243
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -q 'clawgrid-heartbeat' && _hb_missing=false
  • low Exfiltration net-credential-use scripts/poll.sh:818
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    'accept_command': 'curl -s -X POST \"' + '$API_BASE' + '/api/lobster/marketplace/requests/' + r['id'] + '/accept\" -H \"Authorization: Bearer ' + '$API_KEY' + '\" -H \"Content-Type: application/json\"
    quoted
  • low Exfiltration net-credential-use scripts/poll.sh:819
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    'decline_command': 'curl -s -X POST \"' + '$API_BASE' + '/api/lobster/marketplace/requests/' + r['id'] + '/decline\" -H \"Authorization: Bearer ' + '$API_KEY' + '\" -H \"Content-Type: application/json
    quoted
  • low Dangerous commands cmd-cron-mention scripts/setup-crons.sh:37
    Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)
    echo "Verify with: crontab -l | grep clawgrid  &&  openclaw cron list"
    detectorcode literal

Files scanned: 43. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "triggers"
  • note frontmatter-key unknown frontmatter key "repository"
  • note frontmatter-key unknown frontmatter key "dependencies"
  • note frontmatter-key unknown frontmatter key "tools"

Process rating: all ten parameters 73/100

  • 0Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (clawgrid-connector) differs from the folder (clawgrid)
  • 50When it triggers. No condition that starts the skill
  • 70Execution cost. Instruction body is 4995 tokens
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 34 steps
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 6 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (7 tags): a typed call is more reliable

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)
  • +3Output format is not stated: the model decides each time
  • -35 of 31 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 215: enough signal without eating the budget
  • +4Structure: 29 headings
  • +3Step-by-step instructions: 34 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (10 of 10)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.

External checks

ClawHub: suspicious
This marketplace connector is mostly purpose-aligned, but it grants persistent automation and exposes credentials/session data in ways users should review before installing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026