ClawHub
Back to skill

Security audit

CC3PO Humanizer

Security checks for vulnerabilities and agentic risk

Overview

This is a writing-style skill that rewrites provided text and does not request code execution, credentials, persistence, or privileged access.

Use this on prose where a more natural style is desired. For legal, compliance, evidentiary, or sensitive business text, review the output carefully because the skill may make tone and wording changes beyond simple cleanup.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The usage guidance says to use the skill to 'humanize text' and to invoke it directly when editing documents, which is a broad, generic trigger rather than a narrowly scoped activation condition. In agent environments, overly broad invocation guidance can cause the skill to activate on many unrelated writing tasks, increasing the chance it rewrites sensitive, policy-relevant, or security-critical text in ways the user did not explicitly request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The markdown directs the assistant to 'Have opinions,' 'Use "I" when it fits,' and be specific about feelings as part of its default behavior. This is a natural-language policy concern because it pushes a particular communicative persona and voice onto the output without stating that the user can choose or decline that style.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.