Security audit
好省返利助手
Security checks for vulnerabilities and agentic risk
Overview
The skills mostly match ClawHub/Convex maintenance work, but the review helper defaults to running a nested reviewer with full sandbox bypass and can send diffs to fallback review tools, which deserves manual review before installation.
Install only if you trust these skills to operate with your local developer and staff credentials. For the autoreview helper, prefer `--no-yolo` or set `AUTOREVIEW_YOLO=0`, and consider disabling automatic fallback reviewers if repository diffs should not be sent to other configured AI review tools. For moderation and PR workflows, verify the exact command, target, and account before approving any write action.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.