Back to skill

Security audit

Joy Log - 快乐档案

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent joy-journaling purpose, but it automatically saves conversation excerpts and supports sharing generated cards without enough user control or privacy safeguards.

Install only if you are comfortable with the agent automatically saving pieces of your conversations when common positive phrases appear. Before use, prefer disabling auto_capture, requiring explicit confirmation for each saved moment, reviewing or redacting captured text before card generation, and confirming any send to Eric or another recipient.

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:19
Finding

Automatic Capture and Persistent Storage of Conversation Content Without Explicit Consent

Content
View full analysis
Remediation
View remediation
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 (4)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly describes automatic recording and storage of ‘warm moments’ from conversation, but provides no user-facing notice, consent flow, retention warning, or privacy controls. Silent persistence of message content and prior context creates a meaningful privacy risk, especially if users do not realize their dialogue is being archived.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The automatic triggers are common conversational phrases such as ‘开心’, ‘赞’, and laughter variants, so the skill may capture ordinary dialogue without a deliberate user action. Because the skill also stores conversation excerpts and surrounding context, broad triggers materially increase the chance of unintended retention of personal or sensitive content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

Manual commands like ‘记下来’ and ‘这一刻很棒’ are plausible ordinary phrases that may appear in normal conversation rather than as an intentional command. Without strict invocation boundaries, the skill can be triggered accidentally and persist conversation data the user did not mean to save.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill states that generated cards can be sent directly to Eric, but there is no mention of an approval prompt or consent check before sharing. Since the card content is derived from conversation excerpts, direct outbound sharing can expose private or sensitive statements to another person without adequate user awareness.

Content

No source excerpt is available for this finding.