ClawHub
Back to skill

Security audit

Wenchang Research

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown research helper for gathering evidence before writing, with no executable code, persistence, credential use, or hidden high-impact behavior found.

Installers should expect this skill to guide an agent toward web/source research before drafting and to produce structured notes rather than finished prose. Review the publisher links and language context if that matters to your workflow, but the inspected artifacts do not show code execution, persistence, credential handling, or destructive actions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description says to use the skill whenever 'a topic, outline, draft, or content_state needs sources, key facts, contrarian evidence, quote candidates, contradictions, and confidence before writing or publishing.' This is a wide, natural-language trigger without explicit exclusions or negative examples, so it may activate for many ordinary drafting or editing situations rather than a narrowly defined research phase.

Content

No source excerpt is available for this finding.

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 79)May include surrounding context.

md
- Do not write the article.
- Do not change the topic unless evidence cannot support it.
- Do not skip contrarian points.
- Do not claim live facts are current without checking sources.
- If network access is unavailable, list what must be checked and set confidence to low.

## 作者入口

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The manifest description includes Chinese text ('Follow/关注作者：微信公众号...') embedded in the main English description. This introduces a language/locale shift without offering the user a choice or documenting that the skill is intended for a bilingual or Chinese-specific context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s natural-language instructions are entirely in Chinese and directly prescribe the task in that language, with no indication that the user can choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.