ClawHub
Back to skill

Security audit

Superpowers Verification

Security checks for vulnerabilities and agentic risk

Overview

This skill is a verification checklist that tells the agent to run appropriate checks before claiming success, with no hidden code or persistence.

Install this only where the agent can understand the Chinese instructions and where extra verification before completion claims is desired. Expect it to make the agent more conservative about saying work is done and to run relevant checks before reporting success.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation rule is extremely broad: it triggers whenever the agent is about to make any positive progress statement, complete a task, move on, or delegate. This can cause the skill to hijack many ordinary interactions and force verification behavior in contexts where it is unnecessary or impossible, creating prompt-scope interference and reducing reliability of other skills or normal conversation flow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Most of the skill body is written in Chinese without providing a language option or documenting that the environment is Chinese-only. In a multilingual or primarily non-Chinese deployment, this can cause the agent to misread requirements, skip important constraints, or inconsistently apply the verification process, weakening the safety control the skill is meant to enforce.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.