ClawHub
Back to skill

Security audit

Frontier Knowledge Digest

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed science and technology digest generator that searches public sources and saves a local report, with no hidden code or credential access found.

Install this if you want an agent to produce broad science and technology digests from public web sources. Be aware that it may run for general science-news style prompts and that it saves Markdown reports in your Documents folder unless you tell the agent not to save or choose another location.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases include very generic requests such as '科技新闻', '最新论文', 'daily digest', and 'science news', which can cause the skill to activate for broad, ordinary user intents rather than a clearly scoped command. Over-broad activation increases the chance of unintended execution of the skill's workflow, including web searching and later local file save behavior, without the user explicitly asking for this specific skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The 'When to Use' examples are ambiguous and overlap with common conversational requests about news, AI, and papers, so an orchestrator may route many generic queries into this skill. In context, that is risky because this skill performs extensive search and is designed to persist output locally, making accidental invocation more impactful than a read-only summarization skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill directs the agent to save a generated report to a fixed local filesystem path without any explicit consent, preview, or opt-in from the user. Silent local persistence can expose sensitive research interests, create unexpected files, and violate user expectations or host security policies, especially if the skill is triggered unintentionally by broad phrases.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.