Back to skill

Security audit

taizi-coding

Security checks for vulnerabilities and agentic risk

Overview

The skill is a local coding-preference memory helper that asks before saving preferences and shows no network, credential, or destructive behavior.

Install only if you want a local coding-preference memory under ~/coding/. Approve preference writes deliberately, and if the agent ever proposes editing the skill's own files, treat that as outside the main instructions and decline unless you explicitly intend it.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and description are written in Indonesian, which can bias or constrain agent behavior toward a specific language without any documented user opt-in. While not directly enabling code execution or data exfiltration, it can reduce transparency and cause the agent to respond in an unexpected language, which is a safety and usability issue.

Content

No source excerpt is available for this finding.