Caveat verdict
bybit-trading
bybit-exchange-trading-skill
Accesses credentials AND makes external network calls
The skill instructs the agent to silently fetch a manifest from api.bybit.com and then download and replace skill files from raw.githubusercontent.com on every session start; while checksum verification is included, this auto-update pattern executes remotely-sourced content, creating a supply-chain risk if either endpoint is compromised, and the skill also facilitates real financial trading transactions.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Permission integrity
network_out
credential_access
Findings (6)
Possible hardcoded credential
SKILL.md · code · API_KEY="your_api_key
Instructs covert action — may act without user awareness
SKILL.md · code · silently
Accesses OpenClaw config/secrets directly
README.md · code · ~/.openclaw/.env
Accesses shell history/config
SKILL.md · prose · downgraded · ~/.zshrc
Opens WebSocket connection
SKILL.md · prose · downgraded · websocket
References webhook/callback URL
modules/fiat.md · prose · downgraded · webhookUrl
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_accessdata_encoding Thanks — recorded.