ClawHub
Back to skill

Security audit

Blog Embargo

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill gives a coherent publishing checklist for coordinating blog embargo timing with Buffer social scheduling, with no hidden execution or persistence mechanism.

Install this only for the blog and social publishing workflow it describes. Before using it, confirm the intended timezone, Buffer accounts, channel IDs, and social copy approval because it can guide scheduling public posts.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instructions require choosing a specific 'AEST datetime' and prescribe preferred posting times in AEST, which imposes a locale/timezone policy in natural language. The document does not offer an alternative timezone choice or explain that the skill is intentionally limited to an Australia-specific publishing operation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.