ClawHub
Back to skill

Security audit

Human Writing

Security checks for vulnerabilities and agentic risk

Overview

This is a writing-assistance skill with a small local validation script; it does not request sensitive access, persistence, or automatic posting authority.

Install only if you want an agent to help draft or revise public writing in a less polished AI style. Use the voice-preservation guidance for your own writing or with clear permission, and do not use it to impersonate someone else or mislead readers about authorship.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose describes a text-editing or writing-review skill, but the supplied code does not analyze or revise writing at all. Instead, it validates repository packaging and policy compliance: required files, markdown headings/phrases, frontmatter format, and leakage of private artifacts or environment-specific data. This is a materially different primary purpose and includes undeclared capabilities related to filesystem/repository inspection and content scanning.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
4. Did it replace the writer's real nouns and judgement with generic stand-ins?
5. Did it remove useful roughness, side threads, contradiction, or unresolved tension?

If yes to any of these, pause and rewrite before sending. Do not ask the user to catch it.

## Human Voice Rules

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This guidance explicitly encourages preserving a specific person's voice, including their cadence, references, and even deliberate typos, without any guardrail about consent, attribution, or impersonation risk. In a writing-assistance skill focused on avoiding AI tells, that makes the material readily usable to produce convincing deceptive mimicry of a real person rather than merely stylistic editing.

Content

No source excerpt is available for this finding.