ClawHub
Back to skill

Security audit

Self-Critique

Security checks for vulnerabilities and agentic risk

Overview

This skill is a self-review checklist for improving drafts and code, with no executable behavior or hidden data access found.

Install this if you want agents to spend extra time reviewing important outputs before finalizing. Expect it to make responses more deliberate and sometimes longer; it should not be treated as a networking, credential, or automation skill.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
95% confidence
Finding

The description says to use the skill for "any output where quality matters," then lists broad domains like code, writing, analysis, and decisions. For a markdown skill description, this trigger scope is so expansive that it overlaps with common, everyday tasks and does not clearly bound when the skill should or should not activate beyond a few loose examples.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/examples.md (reported line 498)May include surrounding context.

Example Request

bash
curl -X POST https://api.example.com/api/users \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/examples.md (reported line 498)May include surrounding context.

Example Request

bash
curl -X POST https://api.example.com/api/users \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{