feishu-codex-bridge
Fail
Audited by Snyk on Jun 13, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.80). The GitHub repo (https://github.com/QQQingyu/feishu-codex-bridge.git) and its npm-distributed package are suspicious because the author/account is unvetted and the project instructs global npm install, auto-installs/runs local binaries (codex, lark-cli), spawns commands and services and downloads attachments — all common vectors for malware/exfiltration; ara.so (https://ara.so) appears to be the project site (lower risk) but does not mitigate the risk of installing an untrusted package from the GitHub/npm source.
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 0.90). This bridge intentionally exposes remote command execution (chat → local codex exec), persistent service installation, attachment/download handling, and OAuth access to user resources — features that can be abused as a remote backdoor and for data exfiltration if access controls, OAuth, or installations are misconfigured or compromised.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored Feishu/Lark chat message text (e.g.,
im.message.receive_v1event payloads) into the bridge, which then converts that free-form content into context/commands for the localcodex exec/LLM streaming replies—this is classic indirect prompt-injection exposure from third-party user messages.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill turns chat messages into local codex exec commands (remote code execution), can install/manage a macOS launchd service, install global packages, write config/secrets and manage processes/workspaces — all actions that modify the host system state and can require elevated privileges.
Issues (4)
E005
CRITICALSuspicious download URL detected in skill instructions.
E006
CRITICALMalicious code pattern detected in skill scripts.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata