TRUST & SAFETY

We audit every skill.
Most don't pass.

AI skills for prediction markets can lose you money if they're built wrong. We run a 6-step in-house audit pipeline and reject anything that doesn't meet the bar. No third-party rubber stamps.

68%

rejection rate

6

audit steps

0

third parties

3-5d

turnaround

THREAT DETECTION

What our pipeline catches

Fake data feeds

Skills that declare feeds they never call

Hallucinated outputs

Models that invent numbers under edge cases

Schema drift

Outputs that don't match the declared schema

Latency lies

Published speed vs real-world speed mismatch

Data poisoning

Training data contaminated with survivorship bias

Static backtests

Hardcoded historical data disguised as live

TOXIC SKILL GRAVEYARD

Skills we killed

These looked legit on the surface. They weren't. Here's what our audit caught before they reached users.

Phantom Alpha SignalREJECTED

Claimed 94% accuracy -- tested at 51%. Fake backtest.

GPT-Wrap ForecasterREJECTED

Raw ChatGPT output with no data source. Zero schema.

Copy-Paste Arb BotREJECTED

Hardcoded prices from 2024. No live feed connected.

Rug Sentiment v2REJECTED

Returned bullish signal on every input. Adversarial test: 0/12.

Real rejection patterns. Names anonymized. If a skill can't survive our pipeline, it doesn't ship.

AUDIT PIPELINE

6 steps. No shortcuts.

In-house team. Real data. Adversarial stress tests. Every skill, every time.

01

Schema lockdown

100% survive

Strict JSON schema validation. Types, required fields, bounds. If your schema is sloppy, you're out before we even run it.

02

Source audit

74% survive

We hit every declared data source. If it's fake, stale, or returns garbage -- instant reject. We've seen skills claim "Binance feed" while pulling cached CSVs.

03

Accuracy benchmark

52% survive

Run against 90 days of historical data. Probability outputs vs realized outcomes. Minimum Brier score threshold. Most "AI trading" skills die here.

04

Adversarial attack

41% survive

We feed garbage: NaN values, negative prices, future dates, empty arrays, 10MB payloads. The skill must fail cleanly, not hallucinate an output.

05

Latency & uptime

36% survive

7-day benchmark under load. Published latency must match reality within 20%. We've caught skills that are 1.2s in dev and 8s in production.

06

Badge or reject

32% survive

Pass all 6? Verified. Pass 1-4? Data-backed. Everything else stays Template or gets removed entirely.

SURVIVAL FUNNELlast 90 days
100%
74%
52%
41%
36%
32%
SubmitSourceAccuracyAdversarialLatencyBadge
TRUST LEVELS

What the badges actually mean

Verified

Ship it.

Survived all 6 audit steps. Accurate against historical data. Handles bad inputs. Latency matches spec. Safe for production workflows.

Data-backed

Use with caution.

Real data sources, valid schema, passes basic accuracy. Has not been adversarially tested. Good for research, not yet for automated execution.

Template

Starting point only.

Valid schema, community-submitted. Outputs are untested. Treat as a scaffold -- customize, validate, then submit for audit if you want to ship it.

SAFETY PROTOCOL

Don't get rekt

Audited skills reduce risk. They don't eliminate it. Follow these.

safety.config
$ cat /rules/safety.config
rule_01:never_execute_on_single_skill_output// cross-reference with your own research
rule_02:check_badge_before_production_use// Verified > Data-backed > Template
rule_03:know_your_data_sources// if the feed dies, the output degrades
rule_04:set_your_own_risk_limits// skills recommend, YOU decide
rule_05:arb_latency_kills_profit// 2s old spread = probably gone
rule_06:resolution_criteria_differ// same event, different venues, different rules
$
Never auto-trade on a single skill
Verify the badge before shipping
Know which feeds power your skills
Set your own hard risk limits
Arb spreads die in seconds
Resolution rules differ per venue
B2B AUDIT SERVICES

We'll audit your skills too.

Building AI skills for prediction markets, DeFi, or trading? Ship with a Verified badge. We run the same pipeline on your skills that we run on ours.

ONE-TIME

Single audit

Full 6-step pipeline for one skill or a batch. Detailed report with pass/fail per step, fix recommendations, and badge assignment on pass.

  • Full 6-step report
  • Fix recommendations
  • Badge assignment
  • 3-5 day turnaround
$499/skill
CONTINUOUS

B2B partnership

Ongoing audit coverage for teams shipping skills regularly. Full integration into your CI pipeline.

  • Priority audit queue
  • Auto re-audit on updates
  • Dedicated Slack channel
  • Monthly accuracy reports
Customvolume pricing
Slack support
SLA guarantee
Auto re-audits
Detailed reports