AF tabtab
Use TabTab to run AI-powered tasks in a sandboxed multi-agent environment. Supported capabilities: - General agent: open-ended tasks, writing, research, summarisation - Data analysis: upload CSV / Excel files, run analytics, generate insights - Data collection: web scraping and browser automation to collect structured data - Chart generation: produce charts and visualisations from data - Deep research: long-form research with web search and synthesised reports - Database Q&A: natural-language to SQL queries against connected databases - Slide generation: create PowerPoint presentations - Web / HTML generation: produce web pages or UI prototypes Interact via REST API: create tasks, poll status, stream event logs, terminate tasks, and download sandbox output.
As a process F 53/100 · Will not run — References files that are not bundled: scripts/env
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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
- The text references files that are not there: add them or drop the references.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-credential-usescripts/get-events.sh:38Credential used in a network call (verify the destination is the intended service)curl -sf "$URL" -H "Authorization: Bearer $KEY" | jq '.' > "$OUT_FILE"
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/env
Process rating: all ten parameters 53/100
- 0Tools and files. 1 referenced file(s) missing: scripts/env
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 6 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3661 tokens
- 100Progress reporting. Reports progress
- 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)
- +1No license
- +2Single-language instructions
- +3Description length 768: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 6 items
- +3Output format is stated explicitly
- +4Has examples (19 code blocks)
- +3All 9 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.