ClawHub
Back to skill

Security audit

PostNitro Carousel Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PostNitro carousel generator, but users should understand that their content and URLs are sent to PostNitro and may consume account credits.

Install only if you intend to use PostNitro for carousel generation. Treat any text, article URL, X URL, slide copy, and public image URL you submit as data sent to PostNitro, avoid secrets or confidential drafts unless authorized, and expect API-key use plus possible credit charges.

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 (5)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger description is very broad, including generic requests like turning text, articles, or topics into social media content, which can cause the skill to activate in situations where the user did not intend to use a third-party service. Because this skill transmits user-provided content to an external API, over-triggering increases the chance of unintended data disclosure and confusing or unsafe agent behavior.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation does not clearly warn that user text, article URLs, X post URLs, and slide content are sent to PostNitro's external API for processing. This creates a privacy and consent risk, especially if users provide sensitive drafts, proprietary content, or internal URLs without realizing that data leaves the local environment.

External Transmission

Medium
Category
Data Exfiltration
Content
### 1. Generate a carousel with AI

```bash
curl -X POST 'https://embed-api.postnitro.ai/post/initiate/generate' \
  -H 'Content-Type: application/json' \
  -H "embed-api-key: $POSTNITRO_API_KEY" \
  -d '{
Confidence
93% confidence
Finding
The skill explicitly sends user-supplied content to an external endpoint, including freeform text and URLs that may contain sensitive or proprietary information. While external transmission is expected for this integration, it is still security-relevant because there are no documented safeguards, minimization steps, or consent checks around what data gets sent.

Vague Triggers

Low
Confidence
79% confidence
Finding
This JSON file appears to be a manifest/example content file, but it provides no activation description, trigger phrases, or exclusion conditions. If this file is used as part of skill configuration, the absence of trigger specificity could leave invocation behavior underspecified and prone to unintended activation elsewhere in the skill stack.

Missing User Warnings

Low
Confidence
84% confidence
Finding
This markdown file describes sending an `embed-api-key` in request headers and submitting user content, article URLs, or X URLs to an external API, but it does not include any warning about sharing data with a third-party service or handling credentials securely. Under the markdown-file criteria for missing user warnings, the description omits disclosure about privacy and system/data handling implications.

Static analysis

No suspicious patterns detected.