ClawHub
Back to skill

Security audit

Doc Setup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation organizer with disclosed read/fetch and file-output behavior, and I found no hidden execution, persistence, exfiltration, or destructive behavior.

Install only if you want an agent to fetch, read, summarize, and write structured documentation notes. When using it, provide the exact source URLs or folders and the intended output directory, and avoid pointing it at private or authenticated documentation unless you intend that content to be summarized into local notes.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to fetch and organize documentation from external sources and references local resources/scripts, which implies file-read capability, but it declares no explicit tool scope or permissions boundary. Without a declared scope, the agent may inherit broader filesystem access than intended, increasing the risk of reading unrelated local files while processing vague or mixed-source documentation requests.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The invocation description is broad enough to trigger on many generic documentation tasks, which can cause the skill to activate in contexts the user did not intend. In an over-broad activation, the agent may begin extracting, summarizing, or indexing content from sensitive internal docs, private repos, or local files, expanding data exposure and the chance of unsafe tool use.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The validator treats the presence of the Portuguese term "Arquivo" as part of the expected table structure, which imposes a specific language requirement in behavior. There is no visible option for users to choose another language or explanation that this validator is intentionally limited to a Portuguese-localized documentation standard.

Static analysis

No suspicious patterns detected.