SKILLEMALL.ai

BD vexa

Live meeting transcription for Google Meet, Teams, and Zoom. Drop a meeting link — Vexa sends a bot that joins, records, and transcribes in real time. Get transcripts, recordings, shareable links, and post-meeting summaries. Works with any calendar workflow. Self-hostable or use Vexa Cloud.

ClawHub Agent Skills author: DmitriyG228 v0.1.0 15 files body ≈ 2 485 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureData and analyticsAI and agentsPersonal productivitytype and topics are labelled automatically from the skill text
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
80
Quality 40%
89
Run on models
none yet
Process rating
D
47/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Exfiltration net-redirectable-api-key scripts/audit.mjs:38
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Exfiltration net-redirectable-api-key scripts/ingest.mjs:40
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Exfiltration net-redirectable-api-key scripts/onboard.mjs:28
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Exfiltration net-redirectable-api-key scripts/vexa.mjs:103
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment

    Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 47/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (vexa) differs from the folder (skill-vexa)
    • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
    • 60Failures and branches. 2 branches
    • 100Steps. 84 steps
    • 100Execution cost. Instruction body is 2485 tokens
    • 100Running it twice. Mutating operations check current state
    • low 12 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (14 tags): a typed call is more reliable

    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
    • +1No license
    • +2Single-language instructions
    • +3Description length 291: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 84 items
    • +4Has examples (0 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 5 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: suspicious
    The skill mostly does what it claims (meeting transcription) but contains multiple inconsistencies and questionable behaviors—embedded API keys in the bundle, instructions that ask the assistant to persist user secrets to disk, and code that reads/writes OpenClaw/global config—which together are disproportionate to the declared metadata and warrant caution.
    LLM: suspicious (high) · 5 Mar 2026