Back to skill

Security audit

NextFromKnowledge

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local note-to-action helper whose behavior matches its stated purpose, with some mixed Chinese/English presentation to be aware of.

Install only if you want a local CLI/agent skill that reads notes you provide and turns them into action-oriented recommendations. Be aware that much of the guidance and default prompt favors Chinese output, though the local code does not show hidden network, credential, persistence, or automatic publishing behavior.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description presents an end-user skill for analyzing notes, research, and summaries to recommend next actions. The supplied code does not implement any such analysis or transformation. Instead, it is deployment infrastructure: it extracts version and changelog information from local files and invokes clawhub publish to release the package. That is a materially different primary purpose and includes an undeclared external publishing capability, so this is a clear mismatch.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Most of the skill description and usage guidance is written in Chinese, while the file does not state that the skill is China-specific or provide an opt-in language choice. This can violate language/locale policy because it effectively imposes a specific language on users without notice or alternatives.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file’s core skill descriptions, marketplace copy, and install hook text are written in Chinese, while the surrounding release-note structure is in English. This creates a natural-language policy concern because the skill presentation appears to enforce a specific language for user-facing content without opt-in or any explanation that the skill is region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest says the skill should be used to turn 'notes, research, meeting summaries, documents, or knowledge graph outputs' into actions or decisions, which is a very broad set of common user materials. It does not provide limiting conditions, explicit trigger boundaries, or negative examples to clarify when this skill should activate versus other summarization or planning skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The default prompt ends with 'answer in Chinese,' which imposes a specific language regardless of user preference. There is no opt-in language selection or documented region-specific justification in the file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description is written entirely in Chinese and presents the skill identity and behavior in that language, which indicates a language-specific constraint. There is no accompanying indication that users can choose another language or that the Chinese-only presentation is required for a documented region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code emits fixed English headings such as "Bottom Line," "Decision," and "What Is Already Enough" across rendered outputs, while much of the skill logic and content patterns are Chinese. That creates a natural-language locale policy issue because the skill enforces one output language without user opt-in or any documented justification for the constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file includes core user-facing example prompts in Chinese as part of the activation and usage guidance. Because the skill does not state that it is Chinese-only, multilingual by default, or user-language adaptive, the file implicitly privileges one language without an explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The help output includes a Chinese example string ("方案A,方案B") while the rest of the interface is in English. This imposes a mixed-language experience without any documented language selection or opt-in, which can violate language/locale consistency expectations.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This is a manifest file, so vague-trigger checks apply. The description lists broad intents like 'next action, plan, decision, or experiment' from common artifacts such as notes and meeting summaries, but does not specify invocation boundaries, exclusions, or narrow trigger phrases.

Content

No source excerpt is available for this finding.