Back to skill

Security audit

meta-super-agent-integration

Security checks for vulnerabilities and agentic risk

Overview

This skill does not show malicious behavior, but it mostly documents broad meta-agent claims and includes a small learner script that can save user-provided notes locally.

Install only if you are comfortable with a Chinese-language, largely aspirational meta-agent skill. Treat its self-verification and self-evolution claims as documentation unless your environment separately provides those referenced components, and do not pass secrets in learner notes because they may be saved locally.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill claims strong self-verification, reflection, orchestration, and continuous self-evolution capabilities that are not actually implemented. This is dangerous because downstream agents or users may rely on nonexistent safety checks and governance mechanisms, causing over-trust, unsafe automation decisions, or unintended persistence behavior under false assurances.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding

The skill advertises orchestration and persistence-oriented behavior yet declares no explicit tool scope or permission boundaries. In an agent ecosystem, undocumented file-write capability increases the chance of unauthorized local state changes, persistence of unexpected data, or privilege creep when the skill is invoked by higher-level planners.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language description and the entire user-facing skill content are presented in Chinese, with no indication that language selection is optional or tied to a documented regional requirement. This can violate a language/locale policy when users have not opted into that language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation guidance is extremely broad, effectively suggesting the skill can be used directly for an entire task domain without clear trigger constraints, prerequisites, or safety boundaries. Over-broad activation criteria can cause this skill to be selected in inappropriate contexts, amplifying any hidden side effects such as persistence, cross-skill orchestration, or misuse of claimed capabilities.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The only natural-language description in the file is written in Chinese and presents the skill purpose solely in that language, with no indication of user language choice or justified locale restriction. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire skill file is written in Chinese, including headings and operational descriptions, with no indication that the user opted into this language or that the skill is specifically intended for a Chinese-language context. This can violate language/locale policy requirements when a skill implicitly forces a locale-specific experience.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code writes accumulated operation metadata and free-form notes to learned_patterns.json, but provides no confirmation prompt or user-facing notice that data is being persisted. While the module docstring describes recording behavior, it is not a visible runtime disclosure to users invoking the script directly.

Content

No source excerpt is available for this finding.