ClawHub
Back to skill

Security audit

newsletter-writer

Security checks for vulnerabilities and agentic risk

Overview

The skill provides local newsletter drafting with manual compliance review, though its renderer has defects and its optional Windows app needs separate evaluation.

Expect manual compliance review, not automated certification. Correct the CSV/Markdown input mismatch and placeholder bug before relying on generated output, and use trusted inputs in a dedicated output folder. Evaluate the optional Windows executable separately; its published hash does not prove safety.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code partially supports the declared template-rendering purpose, but the explicitly promised compliance checks are entirely absent. It only reads local files and writes rendered Markdown; no unrelated network or email-sending behavior is present. Additionally, the substitution logic wraps already double-braced placeholders in another pair of braces, so it searches for triple-braced tokens rather than the documented double-braced tokens.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

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.

The manifest promises CAN-SPAM and bulk-sender checks, but the implementation only renders templates.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The skill advertises CAN-SPAM and bulk-sender checks, but the supplied rendering code performs no corresponding validation or reporting. Newsletter operators relying on that assurance could distribute messages missing required compliance elements or overlook sender requirements, potentially causing regulatory exposure, delivery failures, or reputational harm. This script only generates files and does not send email, so the impact depends on downstream use; checks elsewhere in the skill have not been established by the supplied evidence.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.