SKILLEMALL.ai
RU Sign in

FC twilio

(no description)

Not recommendedcritical or high security findings · low grade F
modbender/skill-library-mcp Agent Skills author: modbender MIT 24 files · 2 scripts body ≈ 3 951 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Complete Twilio integration for making voice calls, sending SMS messages, and receiving incoming text messages with automatic replies.

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

ProcedureMarketingtype 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
0/100
safety, quality, tests
Safety 60%
0
Quality 40%
0
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
When it triggers w 12
0
Running it twice w 4
30
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: twilio (modbender/skill-library-mcp)

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.

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.

Dangerous commands 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 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.
  2. Add a description to the frontmatter: without it the skill never triggers.
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 · 40

  • high Exfiltration exfil-webhook-url 00-START-HERE.md:113
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    Forwarding  https://abc1….io -> http://loca…000
  • high Exfiltration exfil-webhook-url 00-START-HERE.md:125
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    https://abc1….io/sms
  • high Exfiltration exfil-webhook-url QUICK_REFERENCE.md:39
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    # Copy the URL: https://abc1….io
  • high Exfiltration exfil-webhook-url SKILL.md:273
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    # Forwarding  https://1a2b….io -> http://loca…000
  • high Exfiltration exfil-webhook-url TWO_WAY_SMS_SETUP.md:68
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    Forwarding  https://1a2b….io -> http://loca…000
  • high Exfiltration exfil-webhook-url TWO_WAY_SMS_SETUP.md:200
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    # Forwarding  https://1a2b….io -> http://loca…000
Medium and low: 34
  • medium Exfiltration exfil-webhook-url 00-START-HERE.md:116
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    Copy the HTTPS URL (the `https://abc1….io` part).
    quoted
  • medium Dangerous commands cmd-shell-rc setup.sh:75
    Writes to a shell startup file
    echo "💡 Tip: Add this to your ~/.bashrc or ~/.zshrc to load credentials automatically:"
  • medium Exfiltration exfil-webhook-url SKILL.md:276
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    Your public URL is `https://1a2b….io/sms` (note: `/sms` endpoint)
    quoted
  • medium Exfiltration exfil-webhook-url SKILL.md:282
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    4. Paste: `https://1a2b….io/sms`
    quoted
  • medium Exfiltration exfil-webhook-url TWO_WAY_SMS_SETUP.md:77
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    - Paste your public URL: `https://1a2b….io/sms`
    quoted
  • low Secrets in code secret-high-entropy-token 00-START-HERE.md:71
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export TWILIO_ACCOUNT_SID="AC35…ca9"
    quoted
  • low Exfiltration read-dotenv 00-START-HERE.md:78
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv 00-START-HERE.md:80
    Reads a .env file
    set -a; source .env; set +a
  • low Secrets in code secret-high-entropy-token IMPLEMENTATION_SUMMARY.md:58
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export TWILIO_ACCOUNT_SID="AC35…ca9"
    quoted
  • low Secrets in code secret-high-entropy-token QUICK_REFERENCE.md:13
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export TWILIO_ACCOUNT_SID="AC35…ca9"
    quoted
  • low Exfiltration read-dotenv QUICK_REFERENCE.md:18
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv QUICK_REFERENCE.md:20
    Reads a .env file
    set -a; source .env; set +a
  • low Exfiltration read-dotenv QUICK_START.md:34
    Reads a .env file
    set -a; source .env; set +a
  • low Exfiltration read-dotenv QUICK_START.md:39
    Reads a .env file
    source ~/clawd/skills/twilio/.env
  • low Exfiltration read-dotenv QUICK_START.md:117
    Reads a .env file
    # Re-source .env if needed
  • low Exfiltration read-dotenv QUICK_START.md:118
    Reads a .env file
    set -a; source .env; set +a
  • low Secrets in code secret-high-entropy-token QUICK_START.md:137
    High-entropy token-like string (may be an id, hash or a credential)
    | `TWILIO_ACCOUNT_SID` | Yes | AC35…ca9 |
  • low Secrets in code secret-high-entropy-token README.md:25
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export TWILIO_ACCOUNT_SID="AC35…ca9"
    quoted
  • low Exfiltration read-dotenv README.md:35
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv README.md:41
    Reads a .env file
    set -a; source .env; set +a
  • low Secrets in code secret-high-entropy-token SKILL.md:41
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export TWILIO_ACCOUNT_SID="AC35…ca9"
    quoted
  • low Exfiltration read-dotenv SKILL.md:59
    Reads a .env file
    set -a; source .env; set +a
  • low Exfiltration read-dotenv SKILL.md:325
    Reads a .env file
    source .env  # Load credentials
  • low Exfiltration read-dotenv SKILL.md:337
    Reads a .env file
    source .env
  • low Exfiltration read-dotenv SKILL.md:352
    Reads a .env file
    source .env
  • low Secrets in code secret-high-entropy-token TWO_WAY_SMS_README.md:30
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export TWILIO_ACCOUNT_SID="AC35…ca9"
    quoted
  • low Exfiltration read-dotenv TWO_WAY_SMS_SETUP.md:18
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv TWO_WAY_SMS_SETUP.md:28
    Reads a .env file
    set -a; source .env; set +a
  • low Exfiltration read-dotenv TWO_WAY_SMS_SETUP.md:36
    Reads a .env file
    source .env  # If using .env file
  • low Exfiltration read-dotenv TWO_WAY_SMS_SETUP.md:126
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv TWO_WAY_SMS_SETUP.md:132
    Reads a .env file
    set -a; source .env; set +a
  • low Exfiltration exfil-webhook-url TWO_WAY_SMS_SETUP.md:227
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    - Paste your public URL: `https://your-url.ngrok.io/sms`
    placeholder
  • low Exfiltration exfil-webhook-url TWO_WAY_SMS.md:32
    Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)
    Copy the HTTPS URL (e.g., `https://abc1….io`)
    demoquoted
  • low Dangerous commands cmd-cron-mention TWO_WAY_SMS.md:94
    Mentions editing / listing crontab
    crontab -e

Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error frontmatter SKILL.md: no YAML frontmatter block found
  • error name-missing SKILL.md: frontmatter has no `name`
  • error description-missing SKILL.md: no `description` — the skill can never trigger

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 30Running it twice. 12 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 107 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3951 tokens
  • 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

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 0: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Structure: 43 headings
  • +3Step-by-step instructions: 107 items
  • +4Has examples (41 code blocks)

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