ClawHub
Back to skill

Security audit

Security Guardian

Security checks for vulnerabilities and agentic risk

Overview

This skill performs local secret scanning and Trivy-based container scanning as advertised, with no evidence of hidden persistence, exfiltration, or deceptive behavior.

Install this only if you want an agent to run local scans over project files and Docker images. Review any suggested secret redactions or vault migrations before applying them, and avoid using --force or broad root-level paths unless you intentionally want a wide local scan.

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
94% confidence
Finding
This second mismatch finding indicates the skill advertises CVE scanning with Trivy and structured reporting, while the actual behavior reportedly does not perform those actions. In a security-auditing skill, such misrepresentation is especially risky because users may treat a nonfunctional wrapper as an authoritative scanner and deploy insecure images or leave exposed secrets unaddressed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
This second mismatch finding indicates the skill advertises CVE scanning with Trivy and structured reporting, while the actual behavior reportedly does not perform those actions. In a security-auditing skill, such misrepresentation is especially risky because users may treat a nonfunctional wrapper as an authoritative scanner and deploy insecure images or leave exposed secrets unaddressed.

Lp3

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding
The skill declares executable workflows and references local scripts, but it does not define any explicit tool scope such as allowed-tools or permissions. In an agent environment, missing scope boundaries can let the skill read or operate on unintended files or invoke broader capabilities than reviewers expect, which increases the blast radius if the skill is misused or later expanded.

Static analysis

No suspicious patterns detected.