ClawHub
Back to skill

Security audit

BulkPublish: Get Analytics

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only BulkPublish analytics reference skill with no hidden execution, persistence, or destructive behavior found.

Install only if you want the agent to read and summarize BulkPublish analytics data. Treat the outputs as potentially sensitive business performance information, but the inspected skill itself is only a reference for read-oriented analytics use.

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)

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 31)May include surrounding context.

md
bulkpubli.sh short links, measured by BulkPublish rather than reported by the
platform.

### Never report a 0 without checking `supportedMetrics` first

Every platform entry carries two support fields:

Static analysis

No suspicious patterns detected.