ClawHub
Back to skill

Security audit

Plotlake

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Plotlake API guide for subscribing to feeds and fetching articles, with visible remote API use and no local executable payload.

Install only if you are comfortable sending feed choices, channel names, and submitted feed or website URLs to Plotlake. Do not submit private intranet, authenticated, staging, or tokenized URLs, and confirm before running commands that create, subscribe, add, or delete remote channel sources.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (5)

External Transmission

Medium
Category
Data Exfiltration
Content
homepage: https://github.com/eggyrooch-blip/wewerss
    requires:
      anyBins:
        - curl
        - jq
---
Confidence
95% confidence
Finding
The skill is explicitly designed to interact with an external API at api.plotlake.com and transmit channel metadata and later retrieved content over the network. In this context, the transmission is expected, but it still represents a real data egress boundary that can expose user data, source selections, or article retrieval patterns if not disclosed and controlled.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill sends channel names, subscription choices, and user-provided URLs to a third-party API but provides no privacy or data-handling warning. Users or agents may unknowingly transmit sensitive internal feed URLs or reading preferences to an external service.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill documentation instructs users to create subscriptions and manage channels/sources, which changes remote state, but it does not warn that these actions are persistent and may add or remove subscribed content sources. This can lead to unintended data or configuration changes by an agent acting on behalf of a user without explicit confirmation.

External Transmission

Medium
Category
Data Exfiltration
Content
提交任意 URL（RSS 地址、网站首页），系统自动发现 feed：

```bash
curl -s -X POST "$BASE/api/open/channels/$CHANNEL_ID/sources" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com/feed.xml"}' | jq .
```
Confidence
96% confidence
Finding
The manual source-addition flow sends arbitrary user-provided URLs to the remote Plotlake API for discovery. This is more dangerous than generic outbound traffic because users may submit private intranet, staging, or tokenized URLs, causing sensitive endpoints to be disclosed to a third party and potentially fetched by that service.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The manifest description is written as a Chinese-only operational description, which may impose a language expectation without user opt-in. The policy requires either offering a language choice or clearly documenting and justifying a locale-specific constraint.

Static analysis

No suspicious patterns detected.