Back to skill

Security audit

psych-paper-deconstruction

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward psychology paper analysis template with no hidden execution, persistence, or credential handling.

Installers should know this skill defaults to a Chinese structured report format for psychology coursework. Users who need another language or format should request it explicitly, but there is no evidence of hidden code, data exfiltration, persistence, or unsafe local system 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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The title and usage instructions are written as a mandatory Chinese-language report template, and the file does not offer any user opt-in or alternative language option. Under the policy, forcing a specific language without user choice is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
69% confidence
Finding

The closing sentence frames the output as a fixed Chinese educational deliverable for a specific academic context, reinforcing a single-language workflow without opt-in. While not harmful by itself, it contributes to an undocumented locale constraint.

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 title is presented only in Chinese ('心理学研究方法参考手册') while the rest of the document is in English. This creates a mixed-language presentation that imposes a locale/language choice without offering the user an explicit option or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.