ClawHub
Back to skill

Security audit

Red Team

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed review checklist for validating numerical claims and does not include hidden code, unsafe automation, or disproportionate access.

Install this if you want stricter evidence checks before reporting numerical or scientific results. Expect it to make the agent cite sources, document methods and uncertainty, and label incomplete claims as tentative; review where any optional red-team log is written if you do not want persistent 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
**Required:**
- Exact method name (algorithm, solver, approximation scheme)
- All parameters used (no defaults assumed without checking)
- Sample size / number of data points / convergence level
- Statistical uncertainty or error estimate
- If the computation was interrupted or resumed, say so