ClawHub
Back to skill

Security audit

check

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently requires evidence before reporting success and openly documents its conditional verification-ledger integration.

Use trusted project verification commands. In Brigade-enabled repositories, expect receipt capture and conditional ledger export/import; review the installed tools' destination and retention settings, and check quoted output for sensitive information before sharing.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The description presents a pre-claim verification workflow, but the supplied command performs receipt export/import. The chunk contains no explicit check of completion claims or validation of reported success, and the description does not establish ledger synchronization as part of that workflow. The command's precise effects depend on the external CLI implementation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.