DC nex-vault
Secure local contract and document vault for managing all business agreements and important documents with automatic expiration tracking and compliance alerts. Track diverse documents including contracts (contracten), leases (huurovereenkomsten), insurance policies (verzekeringen), service-level agreements (SLAs), warranties (garanties), software licenses (licenties), subscriptions (abonnementen), maintenance agreements, permits, and certifications. Automatically extract expiration dates, renewal deadlines, termination notice periods (opzegingstermijn), payment terms, and auto-renewal clauses from uploaded documents using intelligent OCR and natural language processing. Receive automatic alerts before expiration (configurable warning windows) so you never miss a renewal deadline or critical termination notice deadline. Optional Telegram notifications keep you continuously informed of upcoming expirations, auto-renewal events, and required actions. Track total monthly and yearly costs across all contracts and subscriptions for budgeting and cost optimization. Search and filter documents by type, contracting party name, date range, or extract key clauses (payment terms, liability limits, confidentiality, termination conditions). Monitor document lifecycle with status tracking (active, expired, pending, terminated). Perfect for agency operators, SME owners, directors, and business managers in Belgium who need systematic contract management, compliance maintenance, and avoidance of costly unexpected renewals.
Secure local contract and document vault for managing all business agreements and important documents with automatic expiration tracking and compliance alerts.
As a process C 56/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice
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 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.
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
- Shorten the description to 1024 characters.
- 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 Dangerous commands
cmd-shell-rcsetup.sh:122Writes to a shell startup fileecho " Add this to your ~/.bashrc or ~/.zshrc"
-
low Exfiltration
exfil-webhook-urllib/alerter.py:128Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"placeholder -
low Dangerous commands
cmd-shell-rcnex-vault.py:484Writes to a shell startup file (string literal in code, not executed)subprocess.run(['bash', '-c', f'echo "export NEX_VAULT_TELEGRAM_BOT_TOKEN={token}" >> ~/.bashrc'])code literal -
low Dangerous commands
cmd-shell-rcnex-vault.py:491Writes to a shell startup file (string literal in code, not executed)subprocess.run(['bash', '-c', f'echo "export NEX_VAULT_TELEGRAM_CHAT_ID={chat_id}" >> ~/.bashrc'])code literal
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1530 chars, limit 1024 - note
description-budgetdescription takes 1530 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 56/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 31 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2367 tokens
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 1530: 120–800 characters recommended
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 31 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.