Caveat verdict
claude-code-assist
cc-helper
Claude Code setup assistant for Chinese developers that guides environment checks, CLI installation, and provider configuration (ANTHROPIC_BASE_URL routing); no exfiltration or deception, credential handling is user-controlled.
⚠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.
Permission integrity
credential_access
agent_memory
Findings (8)
Possible hardcoded credential
SKILL.md · code · TOKEN="ä½ çš„API-Key
Command substitution with curl — remote code execution
references/install-guide.md · code · bash -c "$(curl
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
references/install-guide.md · code · curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
Pipe to bash — executes piped content as shell commands
references/install-guide.md · code · | bash
Recursive delete from root or home — destructive command
references/troubleshooting.md · code · rm -rf ~
References sudo — requests elevated privileges
references/install-guide.md · code · sudo
Accesses shell history/config
references/install-guide.md · code · ~/.zshrc
HTTP request to bare IP address — common in malicious payloads
references/troubleshooting.md · prose · downgraded · http://127.0.0.1
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/C). 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.
agent_memorycredential_access Is this flag fair?
Thanks — recorded.