ClawHub
Back to skill

Security audit

Caveman输出压缩器

Security checks for vulnerabilities and agentic risk

Overview

This skill only changes the assistant’s writing style, with no code execution, data access, network access, or hidden installation behavior found.

Install this only if you want terse compressed responses by default. Avoid using it for medical, legal, safety, accessibility, or other nuanced work where qualifiers and careful wording matter.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Skill globally overrides assistant response behavior for every reply without explicit user opt-in, which can conflict with higher-priority system or product expectations around clarity, safety phrasing, and accessibility. While style-only on its face, always-on compression and removal of hedging or contextual language can degrade safety-critical responses by stripping nuance, qualifiers, or user-appropriate tone.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.