ClawHub
Back to skill

Security audit

Social Posting

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent social-posting integration, but it can publish to real accounts using broad triggers and fallback credentials without clear confirmation controls.

Review this skill before installing. It should be configured to require explicit confirmation before any live or scheduled post, show the target accounts and provider, and avoid global credential fallback unless you intentionally want shared provider accounts to be used.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger text includes a broad catch-all condition ('any cross-platform publishing request'), which can cause the skill to activate in situations the user did not clearly intend. Because this skill can publish to live social accounts, broad activation materially increases the risk of unintended posting or scheduling actions.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The description does not clearly warn users that the skill can publish directly to real social accounts and may fall back to global environment credentials when personal credentials are absent. This weakens informed consent and can lead to posts being sent through shared or unexpected accounts, creating significant integrity and privacy risk.

External Transmission

Medium
Category
Data Exfiltration
Content
| Provider | Role | API Base |
|----------|------|----------|
| **PostForMe** | Primary (cheaper) | `https://api.postforme.dev/v1` |
| **LATE** | Fallback (reliable) | `https://getlate.dev/api/v1` |

Failover order:
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.