ClawHub
Back to skill

Security audit

Data Quality Checker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local data-quality checker with no evidence of hidden behavior, persistence, credential access, network use, or destructive actions.

Before installing, use it on data files you intentionally provide and choose output paths carefully because the script can overwrite a report or generated schema file at a path you specify. Avoid running it on sensitive datasets unless your local environment is appropriate for that data.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
## Exit Codes

- `0` — No warnings or critical issues
- `1` — Warnings found
- `2` — Critical issues found
Confidence
80% confidence
Finding
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs users to run a local script against arbitrary input files and to optionally write reports, but it declares no explicit tool scope or permission boundaries. In an agent environment, missing `permissions` or `allowed-tools` metadata can allow broader-than-intended file read/write access, increasing the chance of reading sensitive files or overwriting unintended paths when the skill is invoked.

Vague Triggers

Medium
Confidence
93% confidence
Finding
Broad trigger phrases like "check data" and "data issues" are likely to match normal conversation and can cause the skill to activate unexpectedly. Unintended invocation matters here because the skill performs file-oriented analysis and may prompt or attempt access to local datasets when the user did not specifically request this capability.

Static analysis

No suspicious patterns detected.