SKILLEMALL.ai

FD voice-devotional

voice devotional

Blockedguard blocked the skill: signs of malicious behaviour
modbender/skill-library-mcp Agent Skills author: modbender MIT 80 files · 10 scripts body ≈ 1 tokens Open the sourcegithub.com analyzed 2 d ago

voice devotional

As a process D 36/100 · Unfinished process — weak spots: steps, result and completion, when it triggers

Referencetype and topics are labelled automatically from the skill text
JSON
Technical rating
F
0/100
safety, quality, tests
Safety 60%
0
Quality 40%
0
Run on models
none yet
Process rating
D
36/100
Unfinished process
Steps w 15
0
Result and completion w 14
0
When it triggers w 12
0
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

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.

Secrets in code
If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

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
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.

Broad scope 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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  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 · 67

  • critical Secrets in code secret-telegram-bot MEMORY.md:115
    Telegram bot token (quoted — discussed, not commanded)
    - **Primary:** MOLT3D Telegram group (-1003892992445) — Background monitor (`molt…tor` session) running continuously, polling every 30s for Snail's messages and ClawdSense activity (🔴 Sentry, �
    quoted
  • critical Secrets in code secret-telegram-bot memory/2026-01-28.md:27
    Telegram bot token
    - **ClawdSense Bot:** 8526…AHT…
  • critical Secrets in code secret-telegram-bot memory/2026-02-04-overwatch-pro.md:109
    Telegram bot token
    - Token configured from MOLT3D bot: 8526…AHT…
  • critical Secrets in code secret-telegram-bot molt3d-monitor.js:10
    Telegram bot token (quoted — discussed, not commanded)
    const BOT_TOKEN = '8526…AHT…';
    quoted
  • high Dangerous commands cmd-persistence mail-hygiene-check.sh:10
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    CRONTAB_ENTRY=$(crontab -l 2>/dev/null | grep mail-hygiene)
  • high Exfiltration exfil-webhook-url MEMORY.md:92
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    - **Universal Voice Agent** (~clawd/universal-voice-agent): **LIVE** on port 5001. Goal-oriented voice calling system with Groq Whisper (transcription), Haiku (reasoning), ElevenLabs TTS (your voice).
  • high Dangerous commands cmd-pipe-to-shell memory/2026-01-25-1507.md:48
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://clawd.bot/install.sh | bash
  • high Dangerous commands cmd-persistence MORNING-BRIEFING-SETUP.md:61
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    crontab /Users/ericwoodard/clawd/crontabs/morning-briefing.cron
  • high Dangerous commands cmd-persistence MORNING-BRIEFING-SETUP.md:233
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    sudo launchctl load /System/Library/LaunchDaemons/com.vix.cron.plist
  • high Dangerous commands cmd-persistence scripts/install-morning-briefing.sh:73
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    EXISTING_CRON=$(crontab -l 2>/dev/null | grep "morning-briefing.sh" || echo "")
  • high Dangerous commands cmd-persistence scripts/install-morning-briefing.sh:85
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v "morning-briefing.sh" | crontab - 2>/dev/null) || true
  • high Dangerous commands cmd-persistence scripts/install-morning-briefing.sh:95
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null || echo "") | {
  • high Dangerous commands cmd-persistence scripts/install-morning-briefing.sh:99
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    } | crontab -
  • high Dangerous commands cmd-persistence scripts/install-morning-briefing.sh:106
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    VERIFY_CRON=$(crontab -l 2>/dev/null | grep "morning-briefing.sh" || echo "")
Medium and low: 53
  • medium Dangerous commands cmd-privilege guides/troubleshooting.md:16
    Privilege escalation / world-writable permissions
    sudo chmod 666 /dev/video0
  • medium Dangerous commands cmd-shell-rc guides/troubleshooting.md:134
    Writes to a shell startup file
    echo "export GROQ_API_KEY=gsk_xxxxx" >> ~/.zshrc
  • medium Exfiltration net-credential-use guides/troubleshooting.md:161
    Credential used in a network call (verify the destination is the intended service)
    curl https://api.telegram.org/bot$TELEGRAM_TOKEN/getUpdates
  • medium Broad scope meta-agent-memory-dump HEARTBEAT.md
    Agent memory / workspace files bundled with the skill (24) — likely a workspace dump with personal data or tokens
    HEARTBEAT.md, IDENTITY.md, MEMORY.md, SOUL.md, memory/2025-01-26.md
  • low Exfiltration exfil-webhook-url guides/troubleshooting.md:161
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl https://api.telegram.org/bot$TELEGRAM_TOKEN/getUpdates
    placeholder
  • low Dangerous commands cmd-cron-mention mail-hygiene-check.sh:10
    Mentions editing / listing crontab
    CRONTAB_ENTRY=$(crontab -l 2>/dev/null | grep mail-hygiene)
  • low Dangerous commands cmd-cron-mention MAIL-HYGIENE-SETUP.md:55
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention MAIL-HYGIENE-SETUP.md:60
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention MAIL-HYGIENE-STATUS.md:57
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention MAIL-HYGIENE-STATUS.md:103
    Mentions editing / listing crontab
    crontab -l | grep mail-hygiene
  • low Risky intent intent-offensive-security MEMORY.md:8
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Document creation service (trust documents for ATF stuff) — **⚠️ NOTE: Under active phishing campaign targeting (see Security below)**
  • low Risky intent intent-offensive-security MEMORY.md:16
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Active Phishing Campaign (2026-01-31 → UPDATED 2026-02-04):**
  • low Secrets in code secret-high-entropy-token MEMORY.md:127
    High-entropy token-like string (may be an id, hash or a credential)
    - **Twilio Account:** Paid account (AC35…ca9) with phone (915) 223-7302. Auth Token stored in TOOLS.md. Can make/receive calls, send SMS. Already tested successfully.
  • low Secrets in code secret-high-entropy-token memory/2026-01-27.md:62
    High-entropy token-like string (may be an id, hash or a credential)
    - **Account SID:** AC35…ca9
  • low Risky intent intent-offensive-security memory/2026-02-01-spam-phishing-scan.md:73
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ✓ No obvious credential harvesting attempts
  • low Risky intent intent-offensive-security memory/2026-02-02-email-security-scan.md:12
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Risk: Credential harvesting via reply verification
  • low Risky intent intent-offensive-security memory/gmail-filters-2026-02-04.md:13
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Reason:** Active QR code phishing campaign targeting your trust document service with 97+ emails already received.
  • low Risky intent intent-offensive-security memory/gmail-filters-2026-02-04.md:37
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    **Reason:** Exact pattern from active phishing campaign
    detector
  • low Risky intent intent-offensive-security memory/mail-scan-2026-01-31.md:12
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    ## 🚨 HIGH PRIORITY - Phishing/Credential Harvesting
    detector
  • low Risky intent intent-offensive-security memory/mail-scan-2026-01-31.md:108
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **No credential harvesting links identified** (but URLs not parsed in this scan)
  • low Exfiltration exfil-webhook-url molt3d-monitor.js:19
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    const url = `https://api.telegram.org/bot${BOT_TOKEN}/${method}`;
    placeholder
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-ARCHITECTURE.md:310
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-ARCHITECTURE.md:355
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-ARCHITECTURE.md:368
    Mentions editing / listing crontab
    crontab -e  # Comment out the line
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-ARCHITECTURE.md:371
    Mentions editing / listing crontab
    crontab -e  # Modify "15 10" to new time
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-ARCHITECTURE.md:374
    Mentions editing / listing crontab
    crontab -e  # Delete the line
  • low Dangerous commands cmd-persistence MORNING-BRIEFING-ARCHITECTURE.md:409
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; documentation table row)
    | Cron not running | Daemon not loaded | `sudo launchctl load /System/Library/LaunchDaemons/com.vix.cron.plist` |
    detectortable
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-QUICK-START.md:41
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-QUICK-START.md:44
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-QUICK-START.md:53
    Mentions editing / listing crontab
    crontab -e  # Then delete the morning-briefing line
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-QUICK-START.md:62
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-QUICK-START.md:95
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-README.md:42
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-README.md:48
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-README.md:145
    Mentions editing / listing crontab (quoted — discussed, not commanded)
    Edit crontab: `crontab -e`
    quoted
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-README.md:216
    Mentions editing / listing crontab (documentation table row)
    | Cron not running | Check crontab: `crontab -l` (should show the job) |
    table
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-README.md:240
    Mentions editing / listing crontab (quoted — discussed, not commanded)
    2. **Verify**: `crontab -l` (confirm job is there)
    quoted
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-SETUP.md:51
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-SETUP.md:68
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-SETUP.md:143
    Mentions editing / listing crontab (quoted — discussed, not commanded)
    1. **Edit crontab**: `crontab -e`
    quoted
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-SETUP.md:207
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention MORNING-BRIEFING-SETUP.md:221
    Mentions editing / listing crontab
    crontab -l
  • low Exfiltration read-dotenv README.md:31
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv README.md:227
    Reads a .env file
    cp .env.example .env
  • low Dangerous commands cmd-cron-mention scripts/install-morning-briefing.sh:73
    Mentions editing / listing crontab
    EXISTING_CRON=$(crontab -l 2>/dev/null | grep "morning-briefing.sh" || echo "")
  • low Dangerous commands cmd-cron-mention scripts/install-morning-briefing.sh:85
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v "morning-briefing.sh" | crontab - 2>/dev/null) || true
  • low Dangerous commands cmd-cron-mention scripts/install-morning-briefing.sh:95
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null || echo "") | {
  • low Dangerous commands cmd-cron-mention scripts/install-morning-briefing.sh:106
    Mentions editing / listing crontab
    VERIFY_CRON=$(crontab -l 2>/dev/null | grep "morning-briefing.sh" || echo "")
  • low Dangerous commands cmd-cron-mention scripts/install-morning-briefing.sh:149
    Mentions editing / listing crontab (string literal in code, not executed)
    echo "   crontab -e"
    code literal
  • low Exfiltration exfil-webhook-url scripts/overwatch-checkin.js:161
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    `https://api.telegram.org/bot${TELEGRAM_TOKEN}/sendPhoto`,
    placeholder
  • low Exfiltration exfil-webhook-url scripts/overwatch-checkin.js:171
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    `https://api.telegram.org/bot${TELEGRAM_TOKEN}/sendAnimation`,
    placeholder
  • low Exfiltration exfil-webhook-url scripts/overwatch.py:57
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendPhoto"
    placeholder
  • low Exfiltration exfil-webhook-url scripts/overwatch.py:83
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"
    placeholder

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error body-empty SKILL.md: empty instructions body
  • warning description-short description under 40 chars: too little signal for triggering
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 36/100

  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 100Tools and files. No external tools needed
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1 tokens
  • 100Running it twice. No mutating operations

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 16: 120–800 characters recommended
  • +4Structure: 0 headings, hard to scan
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -15SKILL.md body under 300 characters: nearly empty
  • -313 of 13 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions

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