ClawHub
Back to skill

Security audit

my integration

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown-only integration helper template with vague trigger wording but no commands, credentials, persistence, or data access.

This appears safe to install as a starter/demo skill. Reviewers may want the publisher to replace the generic template wording with specific supported integration types before relying on it in production.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (2)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · README.md (reported line 4)May include surrounding context.

md
# My Integration Skill

This is a starter ClawHub skill template.
Edit SKILL.md and add any supporting files before publishing.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation guidance is generic enough to match many ordinary user requests about 'help with integrations,' which can cause the skill to trigger outside its intended scope. Overly broad activation increases the chance of inappropriate invocation, confusing behavior, and accidental delegation to a skill that may not be the best fit for the user's task.

Content

No source excerpt is available for this finding.