Back to skill

Security audit

Agent Summary

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed progress-summary helper that reads recent subagent status/history for the stated purpose and does not include executable code or hidden behavior.

Install this only if you want an agent to periodically inspect active subagent progress and summarize recent worker messages. Non-Chinese-speaking users should translate or review the instructions first, and users handling sensitive subagent conversations should be aware that the skill reads recent session history to generate summaries.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description and the body of SKILL.md present the skill behavior and usage guidance in Chinese only. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.