SKILLEMALL.ai

CF dropbox-business

Dropbox Business API integration with managed OAuth. Full admin access to team members, groups, team folders, devices, audit logs, member file access, sharing, and file requests for Dropbox Business teams. This is an admin-level integration that can read, create, update, and delete team resources, access individual members' files and shared folders via Dropbox-API-Select-User, and permanently remove members or folders. All write and delete operations require explicit user approval with specific resource identifiers. Member file access is privacy-sensitive — only use when the user explicitly requests it with a stated business justification. Use this skill when users want to administer Dropbox Business teams. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key. Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn a Dropbox Business connection into automation, in the order they are used: the connection (the first step), a hosted function that runs a Dropbox Business action through the Maton SDK, and a trigger that calls that function on a schedule or on an event. Those sections are the platform's own reference text, shared with the api-gateway skill, with Dropbox Business examples; they add no Dropbox Business capability - Dropbox Business is not an event source, a trigger cannot read Dropbox Business data, and the files under `references/<source>/triggers.md` are the platform

ClawHub Agent Skills author: byungkyu v1.2.4 MIT-0 11 files body ≈ 17 755 tokens Open the sourceclawhub.ai analyzed 8 h ago

Dropbox Business API integration with managed OAuth.

As a process F 55/100 · Will not run — References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md

IntegrationStripeNotionSlackGmailSecuritySoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
C
66/100
safety, quality, tests
Safety 60%
85
Quality 40%
37
Run on models
none yet
Process rating
F
55/100
Will not run
References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Execution cost w 6
10
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.

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. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
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 · 11

✓ No critical or high findings

Medium and low: 11
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Grep Glob
  • low Secrets in code secret-high-entropy-token references/github/triggers.md:1139
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "node_id": "MDIz…DU3"
    quoted
  • low Secrets in code secret-high-entropy-token references/github/triggers.md:1313
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "node_id": "MDEw…jY5",
    quoted
  • low Secrets in code secret-high-entropy-token references/stripe/triggers.md:41
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "balance_transaction": "txn_…GxW",
    quoted
  • low Secrets in code secret-high-entropy-token references/stripe/triggers.md:117
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "evt_…qVg",
    quoted
  • low Secrets in code secret-high-entropy-token references/stripe/triggers.md:144
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "subscription": "sub_…qSY"
    quoted
  • low Secrets in code secret-high-entropy-token references/stripe/triggers.md:180
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "subscription": "sub_…qSY",
    quoted
  • low Secrets in code secret-high-entropy-token references/stripe/triggers.md:194
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "subscription": "sub_…qSY",
    quoted

A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 2122 chars, limit 1024
  • warning body-long SKILL.md body ≈ 17755 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/<source>/triggers.md
  • warning missing-ref reference to a missing file: references/{source}/triggers.md
  • note description-budget description takes 2122 of the ~15000-char shared budget for all skills
  • note edit-residue the text marks something as outdated (lines 696, 1947): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 55/100

Will not run. References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
  • 0Tools and files. 2 referenced file(s) missing: references/<source>/triggers.md, references/{source}/triggers.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 17755 tokens: crowds the task out of the window
  • 30Running it twice. 161 mutating operations with no state check
  • 60Result and completion. Output format stated, no completion criterion
  • 85Steps. 92 steps, 1 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 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 2121: 120–800 characters recommended
  • +1No license
  • +2Single-language instructions
  • +4Structure: 142 headings
  • +3Step-by-step instructions: 92 items
  • +3Output format is stated explicitly
  • +4Has examples (154 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 37.

External checks

ClawHub: clean
The skill is a clearly disclosed Dropbox Business admin integration with high-impact capabilities that are scoped by repeated user-approval and credential-handling rules.
LLM: benign (high) · VirusTotal: · 13 Sept 2026