dr-memory-foundation

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 11:35 PM UTC
• Version: 2.1.1

Overview

This skill openly sets up a local file-based memory folder and templates, with no evidence of hidden network access, credential use, deletion, or unsafe persistence.

Install this only in a workspace where you want a persistent memory structure. Review the generated memory files, especially MEMORY.md and memory/always_on.md, before relying on them because they can influence future agent context.

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

• Rogue Agent: Self-Modification, Session Persistence
• 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)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 96% confidence
• Finding: The skill instructs the agent to create and modify files in the workspace and even references an installer script, but it declares no explicit tool scope or permissions boundary. That creates an authorization gap where a host system or reviewer cannot easily constrain file-write behavior, increasing the chance of unintended or over-broad filesystem changes when the skill is applied.

Session Persistence

Medium

• Category: Rogue Agent

Content

## Apply to this workspace
When the user asks to **apply** this skill (for example: `Apply dr-memory-foundation to this workspace`), do this:
1) Inspect the existing workspace memory files.
2) Create any missing template files from `references/templates/`.
3) Preserve existing notes; merge or relocate content rather than deleting it.
4) Normalize `MEMORY.md` into preferences + indexes only.
5) Ensure `memory/always_on.md` contains a tiny policy header + topic catalog.

• Confidence: 90% confidence
• Finding: This skill is designed to persist information across sessions by inspecting, creating, merging, relocating, and normalizing memory files. Even though the stated purpose is organizational, persistent memory modification can alter future agent behavior, preserve sensitive information, or silently reshape the workspace state if applied without clear user consent and content-boundary rules.

Static analysis

No suspicious patterns detected.