ClawHub
Back to skill

Security audit

Token Saver For Programmer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local text-compression helper with disclosed automatic activation, but users should verify outputs because it can change or omit details.

Install only if you want automatic shortening of developer content. Review any compressed code, logs, configs, or prompts before using them in debugging, audits, production changes, or security-sensitive work because compression may remove context or alter edge-case meaning.

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
97% confidence
Finding

The skill declares broad auto-activation triggers (code, log, config, prompt) that correspond to very common developer inputs, making unintended activation likely during ordinary use. Because the skill performs lossy compression and explicitly admits edge-case logic may differ, accidental activation could silently alter user content, omit important context, or degrade security-relevant details in code, logs, or prompts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The usage text says to send code, logs, configs, or prompts directly and the skill will activate automatically, with no scope limits, content boundaries, or confirmation step. In this context, that is dangerous because the skill is positioned to rewrite high-sensitivity technical material, including logs and prompts, and could strip or alter details needed for debugging, auditing, or secure code review.

Content

No source excerpt is available for this finding.