ClawHub
Back to skill

Security audit

Superpowers Receiving Code Review

Security checks for vulnerabilities and agentic risk

Overview

This code-review coaching skill is coherent and low-risk, though it intentionally makes the agent terse and discourages gratitude language.

Install this if you want the agent to handle review feedback in a terse, verification-first style. Be aware it may avoid normal courtesy phrases like thanks and may privilege feedback from a named reviewer, so adjust or avoid it if that tone or reviewer assumption does not fit your workflow.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly bans gratitude expressions and prescribes a rigid interpersonal communication style without any user opt-in. While not a code-execution or data-exfiltration issue, this is a genuine policy-shaping vulnerability because it can cause the agent to ignore user-preferred tone, produce unnecessarily abrasive responses, and undermine safe, context-appropriate human communication during code review interactions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.