Caveat verdict

gate-dex-trade

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

This skill explicitly exists to execute on-chain token exchange transactions that modify blockchain state, involving real financial assets; while it requires user confirmation and routes through the Gate MCP server, it is designed to execute real swaps and cross-chain bridges with actual funds.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
70
transparency
90
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (8)

Pattern match critical

Possible hardcoded credential

references/mcp.md · code · token: "<mcp_token>

Pattern match critical

Pipe to python — executes piped content as Python code

references/openapi/sign.md · code · | python3

Pattern match high

Long base64 string (100+ chars) — likely obfuscated payload

references/openapi.md · code · 0x095ea7b3000000000000000000000000459e945e8d06c1ed6bffa8b9d135973a98a864e8000000

Pattern match low

Sets world-executable permissions

install.sh · prose · downgraded · chmod 700

Pattern match low

References agent configuration files

install.sh · prose · downgraded · CLAUDE.md

Pattern match low

pip3 install — installs Python packages at runtime

references/openapi/_shared.md · prose · downgraded · pip3 install

Pattern match low

Base64 encoding/decoding

references/openapi/sign.md · prose · downgraded · base64_encode

Pattern match low

Python urllib.request — network access

scripts/check-allowance.py · prose · downgraded · urllib.request

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

network_incredential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API