Aggressive Context Optimizer

• Outcome: Review
• Latest audit: Sep 12, 2026 · 3:28 AM UTC
• Version: 1.0.0-alpha

Overview

The skill is coherent for reducing OpenClaw token usage, but it can persistently rewrite agent configuration after broad triggers without an in-script confirmation step.

Review the proposed config changes before using --apply, especially --apply --aggressive. The skill appears aimed at token-cost reduction rather than data theft or destructive behavior, but it can change how OpenClaw recalls memory, prunes context, and limits tool output across future sessions.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence

Finding

The skill instructs the agent to run a local Python script and describes behavior that implies file reads, file writes, and shell execution, but it does not declare any explicit tool scope or permissions boundaries. This creates a mismatch between advertised behavior and enforcement, increasing the chance that an agent will execute filesystem or shell actions without clear least-privilege constraints or user visibility.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The invocation text uses broad natural-language triggers like 'uses too many tokens,' 'wasteful,' or 'slow responses in long sessions,' which can match many ordinary complaints and cause the skill to activate in situations the user did not intend. Because this skill is 'aggressive and opinionated' and recommends config-changing actions, over-triggering can lead to unnecessary or premature system modifications.

Content

No source excerpt is available for this finding.

subprocess module call

Medium

• Category: Dangerous Code Execution
• Confidence: 70% confidence

Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/context_optimizer.py (reported line 63)May include surrounding context.

python

def _run(cmd: list[str]) -> str:
    return subprocess.check_output(cmd, text=True).strip()


def _extract_config_path(output: str) -> Path:

subprocess module call

Medium

• Category: Dangerous Code Execution
• Confidence: 70% confidence

Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/context_optimizer.py (reported line 173)May include surrounding context.

python

def validate_config() -> tuple[bool, str]:
    proc = subprocess.run(
        ["openclaw", "config", "validate"],
        text=True, capture_output=True, check=False,
    )

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

This is a code file, so SQP-2 applies to safety-relevant file writes. The script performs a persistent configuration change via save_json() and rollback only covers validation failure, not user intent errors; there is no confirmation prompt before modifying the file and no explicit warning at the write point that the user's config will be changed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.