Back to skill

Security audit

Git Standup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Git commit report generator with no artifact-backed signs of hidden execution, exfiltration, persistence, or privilege escalation.

Installers should expect Chinese help text and report examples, and should verify package completeness because the referenced executable is not present in the inspected artifact. Only point it at repositories whose Git history you are comfortable summarizing in a work report.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README describes the skill in Chinese ('分析 Git 提交自动生成工作日报'), indicating a language-specific behavior, but there is no indication that users can choose the output language or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy requirements for user choice or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description, headings, option explanations, and all usage/output examples are written entirely in Chinese, which imposes a specific language on users. The file does not indicate that Chinese is optional, configurable, or justified by a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest’s user-facing description, command description, and help text are entirely in Chinese. This imposes a specific language on users without documenting that the skill is Chinese-only or offering any language/locale choice, which fits the language policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.