Back to skill

Security audit

Editorial Topic Portfolio

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: most checks are okay, but one JavaScript file was only partially inspected, so coverage is incomplete.

The verdict is benign, but confidence is medium and one file was only partially inspected. Consider that coverage gap when deciding whether to install, especially if you plan to rely on behavior involving that file.

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
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 (2)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 196)May include surrounding context.

md
NODE_PATH=<managed-node-workspace> node scripts/notion_topic_adapter.js read > <run-dir>/08-notion-read.json

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 62)May include surrounding context.

md
- Writing the body directly; hand the primary topic to `industry-deep-dive-pipeline`.
- Generating WeChat layout, summaries, covers, social assets, or publish content directly.
- Writing to Notion without confirmation (unless the current workspace has an explicit, persistent standing instruction authorizing routine-review auto-sync).
- Ranking purely by buzz, a single number, or headline spreadability.

## Inputs