condor-strategy

Fail

Audited by Snyk on May 15, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.90). These links point to raw Python scripts and config files in a small/unvetted GitHub repo and a project site, and the provided install instructions explicitly instruct downloading and executing those scripts (via curl + cron/python), which makes them a high-risk vector for malware or backdoors even though the files are on GitHub.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill directly fetches and ingests public market and "Smart Money" leaderboard data via mcporter_call (e.g., fetch_universe -> market_list_instruments and fetch_sm_map -> leaderboard_get_markets), and the agent uses that untrusted, user-derived content to score signals and autonomously create positions, so third-party content can materially influence actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).


MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). Yes. The skill is explicitly a crypto trading strategy with automated execution primitives: it configures a strategy wallet (runtime.yaml WALLET_ADDRESS), installs a runtime and a scanner cron that likely places trades (condor-scanner.py), references trading APIs/ops such as strategy_get_asset_trading_limits, margin/leverage settings, position sizing, entry/exit rules, DSL-managed exits, on-chain RatchetStop, and hard caps for leverage and drawdown. These are specific, purpose-built controls for placing market positions and managing funds on (Hyperliquid) crypto markets — i.e., direct financial execution.

Issues (4)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
CRITICAL
Analyzed
May 15, 2026, 10:51 AM
Issues
4