v1.0.0

Simmer Momentum Trader

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 8:30 AM.

Analysis

This skill matches its trading purpose, but it deserves careful review because it can place live prediction-market trades using an API key and is configured for scheduled automation.

GuidanceReview this carefully before installing. It is a real trading automation template: keep it in dry-run until you understand the strategy, limit the API key and trade amount, restrict the monitored market IDs, and add stronger live-trading safeguards such as per-order approval, budget limits, and fail-closed context checks.

Findings (5)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityHighConfidenceHighStatusConcern

simmer_momentum_trader.py

if not live:
        print("  (Dry run — no order placed. Pass --live to execute.)")
        return

    try:
        result = client.trade(
            market_id=market_id,
            side=signal["side"],
            amount=TRADE_AMOUNT,

This shows the skill defaults to dry-run, but in live mode it directly places trades using the configured amount. Real market orders are high-impact actions, and the artifacts do not show per-order confirmation or hard loss/budget controls.

User impactIf live mode is used, the skill can spend funds or change prediction-market positions automatically based on its signal.

RecommendationUse dry-run first, keep TRADE_AMOUNT low, restrict MARKET_IDS, and add explicit per-order approval, budget limits, and duplicate-trade prevention before running live.

Human-Agent Trust Exploitation

SeverityMediumConfidenceHighStatusConcern

simmer_momentum_trader.py

except Exception:
        return None  # Can't check context, proceed with caution

The code treats a failed context-safeguard check as no reason to skip, which weakens the SKILL.md claim that it always checks market context before trading.

User impactUsers may believe flip-flop and slippage safeguards are always enforced, but a failed safeguard check may not stop later trade execution.

RecommendationChange the safeguard to fail closed for live trades, and document exactly when trading is skipped versus allowed to continue.

Rogue Agents

SeverityLowConfidenceHighStatusNote

clawhub.json

"cron": "*/15 * * * *",
  "automaton": {
    "managed": true,
    "entrypoint": "simmer_momentum_trader.py"

The skill is configured as a managed automaton on a 15-minute schedule. This is purpose-aligned for market monitoring, but it is persistent recurring activity.

User impactThe skill may keep running on a schedule after installation, producing repeated market checks and, if configured for live operation, repeated trade decisions.

RecommendationInstall it only if scheduled monitoring is desired, confirm whether the automaton runs in dry-run or live mode, and monitor logs or disable the schedule when not needed.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceHighStatusNote

clawhub.json

"requires": {
    "pip": ["simmer-sdk"],
    "env": ["SIMMER_API_KEY"]
  }

The skill depends on an unpinned external SDK that will handle the API key and trading calls. This is expected for the integration, but package provenance and version pinning matter for a financial automation.

User impactA changed or compromised dependency could affect how credentials or trades are handled.

RecommendationPin and review the simmer-sdk version before use, especially before enabling live trading.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityMediumConfidenceHighStatusNote

simmer_momentum_trader.py

_client = SimmerClient(
            api_key=os.environ["SIMMER_API_KEY"],
            venue="polymarket",
        )

The skill uses a Simmer API key for a Polymarket venue client. This is expected for the trading purpose, but it is a sensitive account credential.

User impactA broadly scoped or poorly protected API key could allow market access beyond what the user intended.

RecommendationUse the least-privileged API key available, rotate it if exposed, and avoid granting more trading authority than the strategy needs.