ClawHub
Back to skill

Security audit

cs-paper-reading

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only guide for structured computer science paper reading, with minor quality issues but no hidden or high-impact behavior.

Installers should expect this skill to guide the agent through structured academic paper review and report writing. The main caveat is possible over-activation on generic paper-related requests; review the trigger wording if strict routing is important.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list includes very broad phrases such as "read paper," "analyze paper," "academic paper," and "research paper," which can match many normal user requests outside the narrow intended use of this skill. Over-broad activation can cause the agent to invoke this skill unexpectedly, interfering with task routing and potentially steering unrelated academic or document-analysis conversations into this workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

Line L50 includes Chinese text ("合理性") embedded in otherwise English instructions, which imposes a language inconsistency without offering the user a language or locale choice. This matches the policy concern for language/locale violations because the skill does not document or justify the mixed-language requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.