ClawHub
Back to skill

Security audit

Agent Pulse

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight status-check helper with no evidence of hidden access, persistence, credential use, or destructive behavior.

Install this if you want a compact agent availability/status command. Be aware that phrases like asking whether the agent is busy or available may trigger the fixed pulse card, so prefer explicit `/pulse` or `Agent Pulse` if you want predictable behavior.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises broad natural-language triggers such as common Chinese phrases meaning 'are you busy' or 'is now convenient,' which can appear in ordinary conversation and unintentionally invoke the skill. Because the skill forces a fixed response format and is preferred before heavier reasoning, accidental activation can interrupt normal intent handling and cause incorrect or low-context responses.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The standard trigger section includes ambiguous colloquial phrases without disambiguation, which increases the chance of the skill firing on routine social language rather than a deliberate status-check request. In this context, unintended invocation is more dangerous because the skill instructs the agent to return a fixed compact card and avoid conversational explanation, potentially suppressing the user's actual request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger description includes broad natural-language equivalents such as asking whether the agent is busy, interruptible, or able to take work. This lacks a specific bounded phrase list or exclusion criteria, so ordinary conversational queries could unintentionally invoke the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.