Back to skill

Security audit

Agent Swarm

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small in-memory multi-agent coordination library with no evidence of hidden access, persistence, exfiltration, or unsafe privilege use.

Reviewers should note that the documentation is mostly Chinese and the package describes more modules than it actually exports, but the installed code is a limited local coordination helper and does not request sensitive access.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language content throughout the skill file is presented only in Chinese, including the title, feature descriptions, and API documentation. Under the policy, forcing a specific language without user opt-in or documented justification is a language/locale policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description is written entirely in Chinese, which may indicate the skill is intended to present itself in a specific language without offering a user choice. Under the policy for natural-language violations, forcing a specific language without opt-in can be a concern unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This file contains natural-language comments in both English and Chinese, but provides no indication of whether the skill enforces or assumes a particular language for users. Under the language/locale policy check, this can be interpreted as an undocumented language expectation rather than an explicit user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The top-level natural-language comments include a fixed Chinese title and description alongside the English class name, but there is no indication that the skill offers language choice or that the locale restriction is required for a region-specific purpose. This can violate language/locale policy when a skill imposes or assumes a specific language without user opt-in.

Content

No source excerpt is available for this finding.