Back to skill

Security audit

BulkPublish: Using BulkPublish

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed BulkPublish helper for drafting, scheduling, publishing, and measuring social media content, with clear safeguards around live posts and deletions.

Install only if you intend to let the agent help manage BulkPublish-connected social accounts. Review drafts, destinations, recipients, and scheduled times carefully, because publishing, replies, moderation, and deletions can affect real public or private interactions and may not be reversible.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description contains broad activation cues such as 'use whenever the user wants to draft, queue, cross-post, retry or measure social content, or asks about their channels, queue or posting quota,' which can match many ordinary user requests. This increases the chance the agent invokes the skill in contexts where the user did not explicitly intend BulkPublish actions, creating risk of over-collection of account data, unintended scheduling workflows, or prompting toward external tool use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.