ClawHub
Back to skill

Security audit

Markdown Images to R2

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Markdown image publishing helper that plans changes by default and only uploads or rewrites when the user chooses apply flags.

Install only if you intend to let the agent inspect local Markdown image paths and, when explicitly confirmed, upload those images to your configured R2/S3-compatible bucket and rewrite the Markdown. Review the generated plan first, use least-privilege R2 credentials, avoid private images, and do not use --allow-outside-root unless you have checked those paths.

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill describes and encourages operations that read files, write backups and modified Markdown, access environment variables for R2 credentials, and contact an S3-compatible network endpoint, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates a trust and containment gap: an agent may execute broader capabilities than reviewers or policy engines expect, increasing the chance of unintended file modification, credential exposure, or network use during publishing workflows.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The CLI help text and control-flow messaging present --confirm-upload and --confirm-write as the explicit confirmations for external upload and Markdown rewriting. However, the actual side-effecting logic in process/apply_plan only checks args.apply, and performs backup creation and markdown_file.write_text once main's earlier argument validation is bypassed or reused programmatically; the confirmation flags themselves are not enforced at the point of mutation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.