Security audit

hippocampus-memory-engine

Security checks for vulnerabilities and agentic risk

Overview

This memory skill is purpose-aligned but should be reviewed because it encourages broad automatic capture and long-term reuse of conversation and memory data.

Install only if you intentionally want an agent memory system that can persist conversation summaries and other local memory sources across sessions. Before enabling daily sync or session-end capture, confirm exactly what will be written, whether anything is pushed or published through GitHub, how sensitive content is excluded, and how stored memories can be reviewed and deleted.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly describes syncing data to GitHub and Obsidian and writing persistent knowledge files, but it does not warn that user content may be stored, exported, or published outside the current session. In a memory-engine skill, this creates a real risk of unintentional disclosure of sensitive conversation data, credentials, internal notes, or proprietary material through filesystem writes or repository publication.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill describes automatic scheduled ingestion and end-of-session memory capture without any consent, retention, or review controls. That makes ongoing collection of user content easy to trigger silently, increasing the chance that sensitive or regulated data is persistently retained and later surfaced, synced, or exposed beyond the user's expectation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The natural-language description and invocation examples are entirely in Chinese, and the file does not indicate that language selection is optional or that the skill is intentionally limited to a Chinese-only environment. Under the policy, forcing a specific language without opt-in can be a locale-policy issue.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.