ClawHub
Back to skill

Security audit

Time Anchor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local date-math helper, with one overbroad activation rule that users should be aware of before installing.

Install only if you want agents to use a local helper for date calculations. Be aware it may activate on ordinary planning or scheduling language, and verify or customize the configured target dates before relying on the full-anchor output.

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

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill description triggers on very broad terms such as "when," "planning," "scheduling," and general mentions of dates or timeframes, which can cause the skill to activate in many ordinary conversations that do not actually require code execution. Because the skill instructs the agent to use exec to run a local script, over-triggering expands the attack surface and increases the chance of unnecessary tool use or context hijacking in unrelated tasks.

Content

No source excerpt is available for this finding.