vulture-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: 0.80). These URLs point to raw GitHub-hosted Python scripts and runtime/config files with explicit instructions to curl and cron-run them from a third-party repo (Senpi-ai) of unclear reputation — executing unvetted code from raw links is a significant security risk (potential remote code execution/malware).

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

  • Third-party content exposure detected (high risk: 0.90). The scanner clearly ingests untrusted third‑party market/Smart‑Money data via mcporter_call("leaderboard_get_markets") (and related market tools) and uses those live fields (direction, pct, traders, price_chg_*, etc.) to score signals and decisively call create_position (plus the SKILL.md install steps instruct downloading raw files from GitHub), so external public content is read and directly influences tool use and trade execution.

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). The skill is explicitly a trading strategy for crypto perpetuals and defines direct trading API calls and runtime actions. It names specific execution functions (create_position, close_position, edit_position, ratchet_stop_add / ratchet_stop_edit / ratchet_stop_delete, cancel_order, strategy_close / strategy_close_positions), requires a strategy wallet, integrates a producer cron (vulture-scanner.py) that "fires" orders, and specifies leverage, margin per position, max positions, and other execution parameters. These are concrete market-order/position management capabilities (crypto trading execution), not generic tooling. Therefore it grants direct financial execution authority.

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, 10:52 AM
Issues
4
Security Audit — snyk — vulture-strategy