SKILLEMALL.ai

BC deployment-kit

Deploy and maintain services on a VPS with 1 command: build → restart → verify → monitor with heartbeat + Telegram alerts. Complete DevOps package: systemd units, nginx reverse proxy, cron @reboot, watchdog restarts, deploy scripts. WARNING: runs systemd restarts, sudo, nohup/setsid and changes runtime state — only use on services you own, test on staging first.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Northcap Group v1.0.9 MIT-0 5 files · 3 scripts body ≈ 675 tokens Open the sourceclawhub.ai analyzed 35 h ago

Deploy and maintain services on a VPS with 1 command: build → restart → verify → monitor with heartbeat + Telegram alerts.

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerTelegramInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
77/100
safety, quality, tests
Safety 60%
70
Quality 40%
87
Run on models
none yet
Process rating
C
50/100
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 · 9

  • high Dangerous commands cmd-persistence SKILL.md:16
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    4. **Cron @reboot** — services that run without systemd
Medium and low: 8
  • medium Dangerous commands cmd-persistence SKILL.md:3
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    description: "Deploy and maintain services on a VPS with 1 command: build → restart → verify → monitor with heartbeat + Telegram alerts. Complete DevOps package: systemd units, nginx reverse proxy, cr
    quoted
  • low Dangerous commands cmd-background-process scripts/deploy.sh:36
    Starts a background / autostarted process
    nohup python3 "$DIR/server.py" >/tmp/$SVC.log 2>&1 &
  • low Exfiltration exfil-webhook-url scripts/notify.sh:10
    Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)
    curl -s --max-time 10 "https://api.telegram.org/bot$TOKEN/sendMessage" \
    vendor-hostquoted
  • low Exfiltration net-credential-use scripts/notify.sh:10
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -s --max-time 10 "https://api.telegram.org/bot$TOKEN/sendMessage" \
    vendor-host
  • low Dangerous commands cmd-background-process SKILL.md:3
    Starts a background / autostarted process (detector / deny-list definition)
    description: "Deploy and maintain services on a VPS with 1 command: build → restart → verify → monitor with heartbeat + Telegram alerts. Complete DevOps package: systemd units, nginx reverse proxy, cr
    detector
  • low Dangerous commands cmd-background-process SKILL.md:4
    Starts a background / autostarted process (quoted — discussed, not commanded)
    metadata: {"deployment-kit": {"requires": {"bins": ["systemctl", "sudo", "curl", "nohup", "setsid"], "network": ["https://api.telegram.org"], "env": ["TG_BOT_TOKEN", "TG_CHAT_ID"], "files": ["~/.confi
    quoted
  • low Dangerous commands cmd-background-process SKILL.md:57
    Starts a background / autostarted process (detector / deny-list definition)
    - Slow processes: `setsid bash -c '...' </dev/null >/dev/null 2>&1 &` — intentional daemonization (process keeps running after shell exit)
    detector
  • low Dangerous commands cmd-background-process SKILL.md:65
    Starts a background / autostarted process
    - **nohup/setsid:** used intentionally to run services in the background outside the terminal — normal daemon practice, not hidden behavior.

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 50/100

  • 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. 9 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 100Steps. 17 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 675 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

  • +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
  • +1No license
  • +2Single-language instructions
  • +3Description length 364: enough signal without eating the budget
  • +4Structure: 7 headings
  • +3Step-by-step instructions: 17 items
  • +4Has examples (2 code blocks)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

External checks

ClawHub: suspicious
This is a transparent deployment helper, but it gives broad restart and background-process authority with weak service-name and local-file controls.
LLM: suspicious (high) · 21 Aug 2026