SKILLEMALL.ai

BD Webhook Token Security (Zero‑Exposure Edition)

Secure webhook token management using MGC Blackbox. Supports DingTalk, WeCom, Feishu, Telegram, Slack and more. Two execution modes: local script with MGC-stored config, or full zero-exposure via mgc_run. Tokens never exposed to AI models.

ClawHub Agent Skills author: zkeviny v1.2.0 MIT-0 4 files body ≈ 2 016 tokens Open the sourceclawhub.ai analyzed 2 d ago

Secure webhook token management using MGC Blackbox.

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, failures and branches

IntegrationSlackTelegramSecuritytype and topics are labelled automatically from the skill text
JSON
Technical rating
B
79/100
safety, quality, tests
Safety 60%
97
Quality 40%
53
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Failures and branches w 10
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. 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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Exfiltration exfil-webhook-url SKILL.md:69
    Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation of a security skill; the skill's own vendor host)
    | Telegram | bot_token | Plain text | https://api.telegram.org/bot{token}/sendMessage |
    security skillvendor-host

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 5, column 14: description: Secure webhook token management using MGC Blackbox. Supports DingT… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "spec"
  • note frontmatter-key unknown frontmatter key "id"
  • note frontmatter-key unknown frontmatter key "platform_compatibility"
  • note frontmatter-key unknown frontmatter key "changelog"

Process rating: all ten parameters 46/100

  • 0Result and completion. Does not say what the result is
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 14 mutating operations with no state check
  • 40Consistency. Frontmatter name (Webhook Token Security (Zero‑Exposure Edition)) differs from the folder (token-safe-webhook-sender)
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 55 steps, 2 vague phrases
  • 100Execution cost. Instruction body is 2016 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 13 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)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +2Single-language instructions
  • +3Description length 239: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 55 items
  • +4Has examples (6 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.

External checks

ClawHub: suspicious
The skill is documentation-only and mostly purpose-aligned, but it gives agents a concrete path to retrieve stored webhook secrets despite presenting itself as zero-exposure.
LLM: suspicious (high) · 7 Aug 2026