ClawHub
Back to skill

Security audit

response-compression

Security checks for vulnerabilities and agentic risk

Overview

This skill only changes response style to be shorter, with no code execution or data access, but its broad triggers and hedging guidance deserve user awareness.

Install this if you want shorter, more direct responses. Be aware it may activate from broad wording like discussions of efficiency or communication, so users who need nuanced explanations, safety-sensitive advice, or careful uncertainty should invoke it deliberately or narrow the triggers.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Confidence
96% confidence
Finding
The trigger phrases are broad enough to activate during ordinary discussion about tokens, efficiency, communication, or directness, increasing the chance the skill silently influences unrelated interactions. In this skill’s context, unintended activation can systematically reshape model outputs toward brevity, which can suppress nuance, caveats, and safety-relevant detail when the user did not request that behavior.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The instruction to remove hedging language and 'use factual statements' can push the agent to present uncertain conclusions as certain, even when the evidence is incomplete. That is dangerous because it degrades calibrated uncertainty, increasing the risk of overconfident technical, medical, legal, or security advice and making errors harder for users to detect.

Static analysis

No suspicious patterns detected.