ClawHub
Back to skill

Security audit

Anti-Detection Writing

Security checks for vulnerabilities and agentic risk

Overview

The skill is transparent about polishing AI-written text and optional detector measurement, with safeguards around accuracy, disclosure, receipts, and publication.

Install this only if you are comfortable using a writing-polish skill that can measure AI-detector scores when you ask. Follow the destination site's rules and disclosure requirements, and review any public post before authorizing it.

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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill is presented as a writing-polish and detector-testing assistant, but the behavior described includes receipt validation, threshold checking, publication workflow, and artifact integrity handling that go beyond the declared purpose. This mismatch can mislead reviewers and users about what the skill actually does, weakening informed consent and making it easier to smuggle higher-risk actions into a seemingly benign text-editing skill.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill references local file resources such as references/measurement.md, references/evidence.md, references/receipt-format.md, and scripts/validate_receipt.py, which implies file-read capability, but it declares no explicit tool scope or permissions. That creates an authorization boundary problem: an agent may read local artifacts the user did not clearly approve, and the undeclared capability reduces transparency and reviewability.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 39)May include surrounding context.

md
## Publish and report

Honor existing user authorization; do not invent authorization or ask again for an already authorized action. For a public reply, refresh the discussion before posting and reassess if context changed. Match the final body to the reviewed version and, when required, its scan and requested threshold. Update the owned answer when editing, then independently read back its author, exact body, and URL. Do not post a duplicate or claim an answer was accepted without checking.

Report the actual quality findings, scores and warnings when measured, and edit or keep decisions. Missing required review or measurement leaves a candidate unpublished. A detector threshold applies only if requested. A successful local receipt check never authorizes publication.

Static analysis

No suspicious patterns detected.