ClawHub
Back to skill

Security audit

d-token-saver

Security checks for vulnerabilities and agentic risk

Overview

This is a token-saving workflow guide with broad activation language but no hidden code, credential access, or automatic system changes.

Install this if you want the assistant to nudge coding and design work toward shorter prompts and more structured requests. Be aware that it may load broadly for coding/design tasks and may encourage use of connected document, design, or storage tools when available, so keep those actions user-directed.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger definition is overly broad because it allows activation not only on specific token-optimization keywords but also proactively at the start of general coding or design tasks. That can cause the skill to inject process guidance into unrelated workflows, increasing unintended influence over agent behavior and creating opportunities for prompt-scope creep or accidental override of more task-specific instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.