Willow Memory Health

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 7:06 AM UTC
• Version: 1.0.0

Overview

This skill performs a disclosed memory-health audit and only suggests or performs cleanup after user confirmation.

Install only if you are comfortable letting the agent read the memory folder you choose. Review the reported file list before approving archive, merge, qmd update, or memory-summary writes.

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

• 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
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence

Finding

The skill instructs the agent to read arbitrary memory directories and execute shell commands (python3 ..., optionally qmd update) but does not declare any explicit tool scope or permissions. That mismatch is dangerous because consumers or enforcement layers may not realize the skill requires file-read and shell capabilities, reducing transparency and increasing the chance of over-broad execution against user or agent data.

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/memory_health.py (reported line 139)May include surrounding context.

python

def check_dark_qmd(title: str) -> tuple[bool, int]:
    """Run qmd query and check if title surfaces. Returns (is_dark, result_count)."""
    try:
        result = subprocess.run(
            ["qmd", "query", title, "--json", "-n", "5"],
            capture_output=True, text=True, timeout=10,
        )