ClawHub
Back to skill

Security audit

Editorial Topic Portfolio

Security checks for vulnerabilities and agentic risk

Overview

The skill has safeguards for Notion updates, but its research workflow could expose confidential editorial ideas through search queries before checking privacy.

Use public or sanitized inputs until confidentiality is checked before every external search. Limit Notion access to the intended topic database and retain confirmation for updates. The included adapter reads data; enabling writes requires a separately reviewed implementation.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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 52)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

The research workflow sends topic-derived search queries to external services without warning about potential disclosure of private editorial data.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow directs the agent to search externally using topic hypotheses, analytical frameworks, and signature phrasing before applying the positioning and privacy gate. Because inputs can include private Notion topics and unpublished editorial plans, these queries could disclose confidential information to search providers; the prohibition on placing private data in public templates does not protect this separate disclosure path.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.