ClawHub
Back to skill

Security audit

PostKing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PostKing onboarding flow with sensitive billing and posting steps that are purpose-aligned and user-directed.

Install only if you intend to let the agent help manage PostKing onboarding, including credit purchases, brand setup, social account connection, and scheduling a first post. Before any top-up, subscription, or post approval, verify the exact price, tier or pack, platform, content, and schedule in the current conversation.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 64)May include surrounding context.

md
This is a multi-stage flow. Obey these rules throughout:

1. **One stage per turn.** Run the current stage, present the result, then stop and wait for the user. Don't chain into the next stage in the same turn, even on success.
2. **Never reuse remembered values without confirmation.** Brand names, website URLs, social handles, theme choices, and post topics must be reconfirmed in the current conversation — don't pull them from prior sessions or long-term memory without surfacing the value and asking the user to confirm it.
3. **Fail loudly, never silently retry.** If a stage fails, stop, surface the error verbatim, and ask the user how to proceed.
4. **Zero brands means onboarding is required**, not optional — never skip ahead to other work without a brand.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to initiate billing actions, including instant off-session charges when a card is already on file, but it does not require an explicit, transaction-specific user confirmation immediately before the charge. In an agent context, this creates a real risk of unauthorized financial actions or accidental purchases because the agent is operationally empowered to spend money once the user expresses a general preference.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.