Security audit

Memory Sync

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local memory-sync tool, but it can archive raw agent conversations and tool data into a Git-staged vault without built-in redaction.

Install only if you are comfortable with a local tool copying agent conversations, tool outputs, rule files, profile data, project metadata, and skill inventories into an Obsidian vault. Keep the vault private, review generated Sources and review packs before running git sync, leave GIT_PUSH_ENABLED=false unless the remote is private and intended for this data, and avoid scanning conversations that may contain credentials, customer data, private keys, or regulated information.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/main.py:6826
Finding: Unredacted Agent Conversations and Tool Data Can Be Published to a Git Remote
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (91)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The declared purpose frames the skill as memory preservation and sync, but the body authorizes broader behavior: scanning conversation histories across products, parsing local SQLite databases, probing local application homes, exporting transcripts, and capturing project state. This mismatch can cause users or orchestrators to approve the skill under a narrower mental model while it performs substantially more invasive data collection than the top-level description suggests.
Content: No source excerpt is available for this finding.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 180)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 182)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 183)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 184)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 185)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 186)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 187)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 188)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 189)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 190)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 191)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 192)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 193)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 195)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 196)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 197)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 198)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 199)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 200)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 201)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 202)May include surrounding context.
md
python scripts/main.py sync

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 203)May include surrounding context.
md
python scripts/main.py sync

Static analysis

No suspicious patterns detected.