Back to skill

Security audit

clawlite-doc-sync

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped documentation-sync workflow that edits repository docs and can create a docs commit, with no evidence of hidden execution, exfiltration, persistence, or unrelated privilege use.

Install this only if you want an agent to update markdown documentation and potentially create a documentation commit in your repository. Review the generated diff and commit before pushing, especially if you do not read Chinese comfortably.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill content is written as an imperative workflow in Chinese without offering language selection, which can reduce user comprehension of what actions will be taken and what approval points exist. In a skill that can edit files and commit changes, reduced comprehensibility increases the chance of accidental consent or misuse, though this is primarily a usability and safety issue rather than a direct security primitive.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs the agent to make repository edits and create a git commit, but it does not provide a prominent user-facing warning or require explicit confirmation before modifying files and writing commit history. In an automated agent context, this can cause unintended repository changes, silently alter documentation, or create commits the user did not authorize, especially if the skill is invoked in the wrong branch or with incomplete context.

Content

No source excerpt is available for this finding.