ClawHub
Back to skill

Security audit

doc-sync

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed documentation and local change-log helper with limited, purpose-aligned file writes.

Before installing, understand that this skill may update documentation files and may store change summaries and file paths locally under `.gemini`. Review proposed doc and README edits before applying them, and do not use the KB logging workflow for secrets or sensitive content unless local retention is acceptable.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The skill description promises automated documentation synchronization and contextual code-change analysis, but the observed behavior is limited to KB/changelog logging. This mismatch is dangerous because users and higher-level agents may grant trust, invoke it on sensitive repositories, or approve writes under false assumptions about what the skill actually does, creating opportunity for misuse, data integrity issues, or hidden side effects.

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill advertises behaviors that modify files, including README and local changelog storage, but does not declare any explicit tool scope or permissions boundaries. In an agent environment, undeclared write capability increases the risk of unintended or overly broad filesystem modification because the caller cannot clearly assess or constrain what the skill may write.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The script persists user-provided change summaries and file paths to a local JSONL log without any consent, notice, retention control, or sensitivity filtering. In this skill's context, summaries may contain proprietary code details, secrets, or sensitive filenames, so automatic local persistence creates an unintended data exposure and privacy risk even if storage is only on the local machine.

Static analysis

No suspicious patterns detected.