Back to skill

Security audit

情緒小怪獸

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent local emotion-education skill for children, but its mood diary stores sensitive entries on disk and should be treated as private data.

Install only if you are comfortable with mood diary entries being saved locally at ~/.bookshelf-plus/kids/mood_diary.json. On shared or backed-up devices, treat that file as sensitive: review local permissions, delete it when no longer needed, and avoid entering identifying or highly private details.

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/mood_diary.py:51
Finding

Child Mood Records Stored Without Enforced Access Restrictions

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (16)

Tp4

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The stated purpose and the detected behavior do not align: the metadata describes a child-facing emotion tool, while the implementation appears narrower and partly parent-oriented, with several declared features missing. This mismatch is dangerous because reviewers and users may trust the description and grant access or use the skill under false assumptions, especially given the sensitive context of children's emotional data and guidance.

Content

No source excerpt is available for this finding.

os.system() or os exec-family call

High
Category
Dangerous Code Execution
Confidence
85% confidence
Finding

os.system() and os exec-family calls run shell commands with the process's full privileges, enabling arbitrary command execution.

Content

Scanner excerpt · scripts/emotion_calendar.py (reported line 46)May include surrounding context.

python
def clear_screen():
    os.system("cls" if os.name == "nt" else "clear")


# ── Emotion mapping ────────────────────────────────────────────────────

os.system() or os exec-family call

High
Category
Dangerous Code Execution
Confidence
85% confidence
Finding

os.system() and os exec-family calls run shell commands with the process's full privileges, enabling arbitrary command execution.

Content

Scanner excerpt · scripts/emotion_cards.py (reported line 250)May include surrounding context.

python
def clear_screen():
    os.system("cls" if os.name == "nt" else "clear")


# ── Emotion mapping ────────────────────────────────────────────────────

os.system() or os exec-family call

High
Category
Dangerous Code Execution
Confidence
85% confidence
Finding

os.system() and os exec-family calls run shell commands with the process's full privileges, enabling arbitrary command execution.

Content

Scanner excerpt · scripts/emotion_coach.py (reported line 67)May include surrounding context.

python
def clear_screen():
    os.system("cls" if os.name == "nt" else "clear")


# ── Emotion mapping ────────────────────────────────────────────────────

os.system() or os exec-family call

High
Category
Dangerous Code Execution
Confidence
85% confidence
Finding

os.system() and os exec-family calls run shell commands with the process's full privileges, enabling arbitrary command execution.

Content

Scanner excerpt · scripts/mood_diary.py (reported line 31)May include surrounding context.

python
def clear_screen():
    os.system("cls" if os.name == "nt" else "clear")


# ── Emotion mapping ────────────────────────────────────────────────────

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README states that a child's mood diary is stored on disk at a predictable local path but provides no privacy notice, retention guidance, or warning about sensitive data handling. Because the data concerns young children and emotional state, disclosure to other local users, backups, screenshots, or shared machines could expose sensitive behavioral information even without network exfiltration.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explicitly states '全繁體中文' as part of the language style, which imposes a specific language/locale. There is no indication that users can opt into another language, nor is there a documented region-specific justification for this constraint.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill advertises capabilities that imply file read/write and shell use, but the manifest does not declare any tool scope or permissions boundaries. This creates an authorization and review gap: operators and users cannot easily tell what the skill is allowed to access, increasing the risk of unintended filesystem access or command execution if the implementation is invoked.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords include very broad, everyday emotional terms that are likely to match ordinary conversation. Overbroad activation can cause the skill to trigger unintentionally in unrelated contexts, leading to surprise execution, unwanted data collection, or interference with other safer handlers.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill states that a child's mood diary is persisted to a local file, but it provides no clear privacy notice, retention policy, consent flow, or data handling disclosure. Because the data concerns young children and emotional state, undisclosed storage materially increases privacy risk, including unauthorized access by other local users, backup systems, or downstream tooling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This Python file contains user-facing prompts, labels, and messages almost entirely in Chinese, and there is no visible opt-in, fallback, or explanation that the skill is intended only for Chinese-speaking users. Under the policy, forcing a specific language without user choice is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains user-facing natural-language content almost entirely in Traditional Chinese, including the title, prompts, and coaching output. Under the policy rule for language or locale constraints, this is a violation because the skill does not provide any opt-in, language selection, or justification for restricting interaction to a specific language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Nearly all user-facing strings in the program are in Traditional Chinese, which imposes a specific language/locale on users. The policy allows locale constraints only when users are given a choice or when the restriction is clearly documented and justified, neither of which appears here.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This skill stores sensitive emotional diary entries for young children in a predictable file under the user's home directory without any user-facing disclosure, consent, retention notice, or access-control hardening. Because the content includes mood, triggers, timestamps, and notes about minors, local storage can expose private information to other local users, backup systems, synced folders, or anyone with access to the account.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This code presents its title and interactive content primarily in Traditional Chinese, while also including English in the header, but there is no indication that the user can choose their preferred language or locale. The policy specifically calls for flagging language or locale constraints when a skill effectively forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This skill is described as an interactive tool for helping young children recognize and express emotions, but clear_screen() invokes os.system to run cls or clear. Terminal clearing is not a core emotional-coaching capability, and spawning shell commands is an unnecessary execution capability for the stated purpose.

Content

No source excerpt is available for this finding.