ClawHub
Back to skill

Security audit

BulkPublish: Bulk Publish

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for BulkPublish media and post management, but it documents destructive media and bulk post actions without clear confirmation or reversibility guidance.

Install only if you are comfortable letting the agent help upload, schedule, publish, reschedule, and delete BulkPublish media or posts. Before any delete or bulk action, require the agent to show the exact mediaId or post IDs, the intended action, and wait for your explicit approval.

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
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly exposes a delete_media capability but provides no user-facing warning, confirmation guidance, or mention that deletion is destructive and may be irreversible. In an agent setting, this increases the chance of accidental or over-broad deletions, especially when the model is asked to manage media in bulk and may invoke destructive actions without adequately signaling risk to the user.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.