Back to skill

Security audit

meta-toolchain-orchestrator

Security checks for vulnerabilities and agentic risk

Overview

The skill is not overtly malicious, but it advertises powerful self-improving orchestration while shipping weakly scoped persistent learning behavior and unsupported safety claims.

Review this before installing. Use it only in a sandboxed environment unless the publisher adds clear tool permissions, write-path limits, validation for learned state, and working implementations for the claimed verification and orchestration features. Do not rely on its advertised self-verification or self-evolution guarantees as shipped.

Vulnerability Patterns
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T02 · Agent Memory Poisoning

Warning
Location
scripts/learner.py:10
Finding

Untrusted Input Written to Persistent Agent Learning State

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)) ``` ### Technical Analysis The script accepts its second command-line argument as an unrestricted note and appends it directly to the persistent `patterns` collection in `learned_patterns.json`. It does not validate the note's origin, content, structure, semantics, or length. The skill documentation characterizes this file as cross-session learning state used by a broader reflection and evolution process. If another agent component subsequently interprets these entries as trusted learned guidance, an attacker who can influence the command-line note can persist arbitrary rules or misleading instructions across sessions. The included script does not itself execute or interpret the stored text. Exploitation beyond state corruption therefore depends on a downstream agent or evolution component consuming `patterns` as trusted guidance. ### Attack Path 1. An attacker supplies content through a task, operation result, or other input that reaches the learner invocation. 2. A caller passes the attacker-controlled content as the second command-line argument to `learner.py`. 3. The script assigns that argument to `rec` without validation. 4. `record()` appends the content to the persistent `patterns` array. 5. The modified state remains in `scripts/learned_patterns.json` across later invocations. 6. If a downstr ...[truncated 693 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
scripts/learned_patterns.json:5
Finding

User-Specific Filesystem Path Exposed in Distributed State

Content
View full analysis
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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill makes expansive claims about self-verification, self-reflection, super-agent orchestration, and continuous self-evolution, but the described implementation does not substantiate those controls. This is dangerous because operators may trust the skill to provide safety or validation guarantees that do not actually exist, leading to unsafe automation decisions, over-trust, or execution without the promised checks.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill advertises orchestration, verification, reflection, and learner-style behavior, which implies it may write logs, plans, or state, yet it declares no explicit tool scope such as permissions or allowed-tools. Missing tool declarations weaken least-privilege controls and make it harder for a host to constrain file-write behavior safely, increasing the risk of unintended or overbroad writes if the skill is executed in an environment that infers capabilities loosely.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The natural-language description and usage instructions are written entirely in Chinese, and the file does not offer an opt-in choice of language or explain that the skill is region-specific. Under the policy, forcing a specific language without user choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. That can violate language/locale policy requirements when users are not given an explicit opt-in or justification for the restriction.

Content

No source excerpt is available for this finding.