SKILLEMALL.ai
GitHub ↗ RU Sign in

DD bluebubbles-healthcheck

Diagnoses and auto-heals BlueBubbles ↔ OpenClaw iMessage connectivity. Use when: iMessages stop arriving after a gateway restart, webhook connection is broken, or user reports messages not coming through. Runs a 4-step diagnostic and auto-fixes webhook backoff, stale registrations, and gateway issues.

Not recommendedlow grade D
ClawHub Agent Skills author: amzzzzzzz v0.1.3 8 files · 3 scripts body ≈ 1 315 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerInfrastructureData and analyticstype 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
D
50/100
safety, quality, tests
Safety 60%
30
Quality 40%
80
Run on models
none yet
Process rating
D
45/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

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

    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 · 14

    ✓ No critical or high findings

    Medium and low: 14
    • medium Exfiltration exfil-secret-in-url references/troubleshooting.md:107
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
      curl "http://127.0.0.1:1234/api/v1/ping?password=…"
      quoted
    • medium Exfiltration net-credential-use references/troubleshooting.md:107
      Credential used in a network call (verify the destination is the intended service)
      curl "http://127.0.0.1:1234/api/v1/ping?password=…"
    • medium Exfiltration exfil-secret-in-url references/troubleshooting.md:110
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
      curl "http://127.0.0.1:1234/api/v1/webhook?password=…"
      quoted
    • medium Exfiltration net-credential-use references/troubleshooting.md:110
      Credential used in a network call (verify the destination is the intended service)
      curl "http://127.0.0.1:1234/api/v1/webhook?password=…"
    • medium Exfiltration exfil-secret-in-url references/troubleshooting.md:116
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
      curl "http://127.0.0.1:1234/api/v1/server/logs?password=…" | grep -i "webhook\|delivery\|backoff"
      quoted
    • medium Exfiltration net-credential-use references/troubleshooting.md:116
      Credential used in a network call (verify the destination is the intended service)
      curl "http://127.0.0.1:1234/api/v1/server/logs?password=…" | grep -i "webhook\|delivery\|backoff"
    • medium Exfiltration net-credential-use scripts/diagnose.sh:61
      Credential used in a network call (verify the destination is the intended service)
      HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" --max-time 5 -H "Authorization: Bearer ${BB_PASSWORD}" "${BB_URL}/api/v1/ping" 2>/dev/null || echo "000")
    • medium Exfiltration net-credential-use scripts/diagnose.sh:77
      Credential used in a network call (verify the destination is the intended service)
      WEBHOOK_RESPONSE=$(curl -s --max-time 5 -H "Authorization: Bearer ${BB_PASSWORD}" "${BB_URL}/api/v1/webhook" 2>/dev/null || echo "{}")
    • medium Exfiltration net-credential-use scripts/diagnose.sh:133
      Credential used in a network call (verify the destination is the intended service)
      SERVER_INFO=$(curl -s --max-time 5 -H "Authorization: Bearer ${BB_PASSWORD}" "${BB_URL}/api/v1/server/info" 2>/dev/null || echo "{}")
    • medium Exfiltration net-credential-use scripts/diagnose.sh:136
      Credential used in a network call (verify the destination is the intended service)
      LOGS_RESPONSE=$(curl -s --max-time 5 -H "Authorization: Bearer ${BB_PASSWORD}" "${BB_URL}/api/v1/server/logs?count=50" 2>/dev/null || echo "{}")
    • medium Exfiltration net-credential-use scripts/diagnose.sh:155
      Credential used in a network call (verify the destination is the intended service)
      MSG_COUNT=$(curl -s --max-time 5 -H "Authorization: Bearer ${BB_PASSWORD}" "${BB_URL}/api/v1/message/count" 2>/dev/null | python3 -c "
    • medium Exfiltration net-credential-use scripts/reset-webhook.sh:56
      Credential used in a network call (verify the destination is the intended service)
      WEBHOOKS=$(curl -s --max-time 10 -H "Authorization: Bearer ${BB_PASSWORD}" "${BB_URL}/api/v1/webhook" 2>/dev/null)
    • medium Exfiltration net-credential-use scripts/reset-webhook.sh:85
      Credential used in a network call (verify the destination is the intended service)
      curl -s -X DELETE --max-time 10 -H "Authorization: Bearer ${BB_PASSWORD}" "${BB_URL}/api/v1/webhook/${id}" > /dev/null 2>&1
    • medium Exfiltration net-credential-use scripts/reset-webhook.sh:128
      Credential used in a network call (verify the destination is the intended service)
      VERIFY=$(curl -s --max-time 10 -H "Authorization: Bearer ${BB_PASSWORD}" "${BB_URL}/api/v1/webhook" 2>/dev/null)

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 45/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 2 mutating operations with no state check
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 100Steps. 24 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1315 tokens
    • 100Progress reporting. Reports progress
    • 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)
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • -42 reference files, but SKILL.md never points to them: the model will not open them
    • +1No license
    • +2Single-language instructions
    • +3Description length 302: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 24 items
    • +4Has examples (7 code blocks)
    • +3All 3 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

    External checks

    ClawHub: suspicious
    This skill is for a real local repair task, but its auto-heal path can delete webhook settings, restart OpenClaw, and expose the BlueBubbles password if misused.
    LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026