Back to skill

Security audit

meta-agent-team-orchestration

Security checks for vulnerabilities and agentic risk

Overview

This skill is not clearly malicious, but it asks an agent to run broad self-evolving orchestration and persist free-form learning notes without adequate controls.

Review this carefully before installing. It is best suited only for users who intentionally want experimental agent orchestration with local learning state. Do not use it where task notes may include secrets or untrusted instructions unless the learning file is reviewed, bounded, or disabled.

Vulnerability Patterns
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • 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
Findings (1)

T02 · Agent Memory Poisoning

Warning
Location
scripts/learner.py:13
Finding

Unvalidated Persistent Agent-Learning Records

Content
View full analysis
1 else True rec = (sys.argv[2] if len(sys.argv) > 2 else "") print(json.dumps(record(ok, rec), ensure_ascii=False)) ``` The persistent-learning behavior is also explicitly documented in `SKILL.md`, including the use of a self-reflection loop, forced learner integration, and cross-session evolution. ### Technical Analysis The command-line argument at `sys.argv[2]` is accepted as an arbitrary note and passed directly to `record()`. When nonempty, the note is appended to the persistent `patterns` collection and written to `scripts/learned_patterns.json`. No validation, normalization, provenance tracking, trust classification, content-length restriction, retention policy, or approval step is applied before persistence. The documented design intends these records to participate in a cross-session meta-evolver and reflection workflow. Consequently, attacker-controlled task content can be promoted into persistent agent state. The script itself does not interpret or execute stored notes. Exploitation therefore depends on the documented downstream learning or reflection workflow later consuming these records as behavioral guidance. This is a persistent memory-poisoning weakness rather than direct code execution. ### Attack Path 1. An attacker supplies malicious, misleading, or instruction-like text through task content or another input that is recorded as a learner note. 2. The orchestration workflow invokes `learner.py`, passing that content as the second command-line argument. 3. `sys.argv[2]` is assigne ...[truncated 1066 chars]
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill makes strong claims about self-verification, self-reflection, super-agent orchestration, and continuous self-evolution, but the file provides only descriptive text and no concrete implementation or enforceable safeguards. This can mislead downstream users or agents into over-trusting the skill's reliability, verification, and autonomy properties, which may cause unsafe delegation or acceptance of unverified outputs.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains natural-language instructions and descriptions that force a specific language/locale without indicating user choice. Under the policy, language constraints should either be optional or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The entire report is written in Chinese, and there is no indication that language selection is optional or constrained by a region-specific requirement. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation applicable to all file types.

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 operational data and free-form notes to learned_patterns.json, but there is no user-facing prompt, print/log notice before the write, or warning comment/docstring explaining that invocation data will be persisted. Because the file stores potentially user-supplied note content, the persistence behavior should be disclosed clearly.

Content

No source excerpt is available for this finding.