ClawHub
Back to skill

Security audit

Demo Note Polisher

Security checks for vulnerabilities and agentic risk

Overview

This is a simple note-polishing skill that rewrites user-provided text and does not request unusual access or run code.

This skill is appropriate for routine rewriting and summarizing of notes, emails, and updates. As with any writing helper, review outputs for accuracy before sending, especially if the text contains sensitive, legal, medical, financial, or business-critical details.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
5. Mark uncertainty instead of inventing details.
   If key information is missing, surface it as an open question or a neutral placeholder.

## Output Rules

- Keep the same language as the input unless the user requests another language.
- If the input mixes languages, normalize to the dominant language unless the user wants bilingual output.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is broadly scoped around common rewriting and polishing requests, which can cause it to trigger on a wide range of generic user inputs without clear boundaries. In an agent routing system, this increases the chance the skill is invoked in contexts where another skill or stricter policy should apply, potentially leading to over-collection or transformation of sensitive user text.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.