Back to skill

Security audit

Agent Optimizer.Skip

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed agent-performance optimizer, but its scripts use unchecked agent IDs in workspace paths, which could let a user read or overwrite another agent's optimizer data if filesystem permissions allow it.

Review before installing in any shared or multi-agent workspace. Only run these scripts for agent IDs you control, avoid putting secrets in trajectory records, and add agent-id validation plus path containment checks before relying on the report-writing script.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
scripts/analyze_trends.py:14
Finding

Unvalidated Agent Identifier Enables Cross-Agent Path Traversal

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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill documentation is written entirely in Chinese, including the title, description, and usage guidance, with no indication that other languages are supported or that Chinese is required for a region-specific purpose. This creates a natural-language policy concern because it effectively imposes a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill documents and encourages file read/write behavior across /workspace/subagents/{agent_id}/optimizer/* but does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization ambiguity: an agent may gain broader filesystem capabilities than a reviewer expects, and the dynamic agent_id path construction increases the risk of unintended file access if callers supply unsafe values.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The prompt template explicitly instructs the agent in Chinese and specifies output requirements in Chinese, which effectively forces a specific language/locale. The file does not indicate that this language choice is optional, user-selected, or required for a region-specific use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script’s docstrings, usage/help text, and user-facing print messages are all in Chinese, including the CLI description and status output. This imposes a specific language on users without opt-in or explanation, which matches the natural-language locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring, usage description, and later user-facing print strings are written in Chinese, which imposes a specific language on users. The file does not provide any opt-in, localization setting, or justification that this skill is intended only for Chinese-speaking or region-specific use.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The module docstring and CLI description state that this script generates an optimization report, but execution will fail at the first use of defaultdict because it is never imported. This is an intent-code divergence because the documentation presents the tool as usable while the implementation cannot complete as written.

Content

No source excerpt is available for this finding.