Security audit

memoir

Security checks for vulnerabilities and agentic risk

Overview

This memoir skill is coherent and not malicious, but it automatically saves highly personal life-story content to local Markdown files without clear consent, deletion, or protection controls.

Install only if you are comfortable with personal memoir entries being saved locally as Markdown files. Before using it, confirm where the files are stored, whether you can disable autosave, review or redact entries before saving, and delete stored notes later.

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: SKILL.md:30
Finding: Automatic Plaintext Storage of Sensitive Memoir Data
Content: View full analysis
Remediation: View remediation

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)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases include very common terms such as “回忆录” and “人生故事”, which can appear in ordinary conversation and cause unintended activation of the skill. Because this skill is designed to elicit and persist highly personal life-history content, accidental invocation can lead to unanticipated collection or storage of sensitive personal data.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly states that each collection session is automatically saved to local files, but it does not clearly warn the user that intimate biographical details, family information, relationships, hardships, and other sensitive data will be written to disk. In this context, the omission is especially risky because memoir collection naturally solicits long-form personal and potentially confidential information, increasing privacy, exposure, and retention risks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The topics_order values are specified entirely in Chinese, which imposes a specific language on the skill's behavior through configuration. There is no accompanying option in this file to let the user select another language or explicitly opt in to Chinese output.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.