Back to skill

Security audit

Tvs Pullread

Security checks for vulnerabilities and agentic risk

Overview

This is a small Git review helper that asks the agent to analyze remote diffs and optionally help with merges; its network Git use is expected for that purpose.

Install this if you want a Chinese-language helper for reviewing incoming Git changes. Before using it in sensitive repositories, remember that git fetch contacts the configured remote and may use your normal Git credentials; approve any pull or merge only after reviewing the summarized changes.

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
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description and operating instructions are entirely in Chinese and present the skill behavior as Chinese-first, but do not offer the user a choice of language or state that the skill is intentionally limited to a Chinese-speaking context. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to run git fetch, which performs remote network access and may contact a configured Git remote without first informing or obtaining consent from the user. In an agent setting, hidden network activity can surprise users, leak repository metadata to external infrastructure, or violate expectations in restricted environments, even if the command is common and not inherently malicious.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.