ClawHub
Back to skill

Security audit

PostKing · Brand Voice

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped PostKing writing helper that lists saved voice profiles and rewrites or checks user-provided text through disclosed PostKing tools.

Install only if you intend to use PostKing for brand-voice rewriting and quality checks. Review rewritten content before publishing, avoid submitting sensitive text unless your PostKing setup is appropriate for it, and follow any required AI-authorship disclosure rules.

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
Content
## CLI fast path

`pking voice list` lists saved voices (equivalent to `list_voices`). Beyond that, the MCP path above is primary — do not assume additional `pking` flags exist for rewrite/humanize without checking `pking --help` first.

## Expected Output
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.

Static analysis

No suspicious patterns detected.