Back to skill

Security audit

Literature Daily Report

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a literature-report tool, but it automatically shares or writes results to external/shared destinations without enough user control.

Review before installing. Use it only if you are comfortable with automatic local report creation, ClawLib copies, Zotero group-library writes, and Matrix report delivery. Prefer disabling or removing Matrix sending, requiring an explicit Zotero group ID, using a narrowly scoped Zotero API key, and avoiding full environment inheritance to external helper scripts.

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 (4)

other

Warning
Location
scripts/literature_collector.py:1174
Finding

Automatic Undeclared Transmission of Generated Reports to Matrix

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/literature_collector.py:389
Finding

Complete Process Environment Exposed to an External Zotero Script

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/literature_collector.py:242
Finding

arXiv Metadata Retrieved over Unencrypted HTTP

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/literature_collector.py:31
Finding

Automatic Zotero Writes Default to a Hardcoded Shared Group

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (20)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared purpose focuses on generating literature reports, but the body additionally performs external writes to Zotero, local replication to ClawLib, and references outbound sending behavior not reflected in the top-level description. This mismatch is dangerous because users and policy layers may approve the skill for summarization while hidden or under-disclosed side effects transmit or duplicate data beyond the expected scope.

Content

No source excerpt is available for this finding.

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
89% confidence
Finding

The code copies the entire process environment and passes it to a child process that runs an external script. This can unintentionally expose unrelated secrets, tokens, and service credentials to that script and any dependencies it loads, violating least-privilege and expanding the blast radius if the helper script is compromised.

Content

Scanner excerpt · scripts/literature_collector.py (reported line 389)May include surrounding context.

python
def get_zotero_collections_for_group():
    """获取 Group Library 下的所有收藏夹(按分类)"""
    try:
        env = os.environ.copy()
        if ZOTERO_GROUP_ID:
            env["ZOTERO_GROUP_ID"] = ZOTERO_GROUP_ID

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill describes capabilities requiring environment access, file reads/writes, network access, and shell execution, but it declares no explicit tool scope or permissions boundaries. This creates an overbroad trust model where an agent may invoke powerful actions without user-visible constraints, increasing the chance of unintended file modification, data exfiltration, or command execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description states 中文格式报告输出, and later sections describe structured Chinese summaries and formatting as the default behavior. This appears to enforce a specific language/locale without user opt-in, which matches the policy violation criteria for language constraints.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill states that generated reports are automatically synced into an additional local directory, but it does not present this as a user-facing warning or optional action. Automatic replication increases the risk of unintended disclosure, stale copies, and writes into broader shared workspaces where other tools or users may access the content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill automatically ingests bibliographic entries into a Zotero Group Library, which transmits metadata to an external service, yet it does not provide a clear user-facing privacy or transmission warning. Even if only article metadata is sent, this can reveal research interests, project focus, or organizational activity patterns to external systems or shared group spaces.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file is entirely written in Chinese and provides no indication that users may choose another language or that the Chinese-only requirement is intentional for a region-specific or audience-specific purpose. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill's stated purpose is literature fetching, filtering, summarization, report output, and scheduling. Spawning a separate Python process to execute another skill's Zotero script introduces cross-skill execution capability that is not an obvious requirement for generating a daily literature report.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/workflows.md (reported line 70)May include surrounding context.

md
"""从 bioRxiv 获取摘要"""
    try:
        # bioRxiv API
        api_url = f"https://api.biorxiv.org/details/{doi}"
        response = requests.get(api_url, timeout=15)
        response.raise_for_status()
        data = response.json()

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/literature_collector.py (reported line 220)May include surrounding context.

python
"""从 bioRxiv 获取摘要"""
    try:
        # bioRxiv API
        api_url = f"https://api.biorxiv.org/details/{doi}"
        response = requests.get(api_url, timeout=15)
        response.raise_for_status()
        data = response.json()

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/literature_collector.py (reported line 706)May include surrounding context.

python
"""从 bioRxiv 获取摘要"""
    try:
        # bioRxiv API
        api_url = f"https://api.biorxiv.org/details/{doi}"
        response = requests.get(api_url, timeout=15)
        response.raise_for_status()
        data = response.json()

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/literature_collector.py (reported line 743)May include surrounding context.

python
"""从 bioRxiv 获取摘要"""
    try:
        # bioRxiv API
        api_url = f"https://api.biorxiv.org/details/{doi}"
        response = requests.get(api_url, timeout=15)
        response.raise_for_status()
        data = response.json()

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The docstring and logic explicitly state that generated summaries should always use Chinese format, regardless of source language. This is a natural-language locale policy issue because it imposes a specific language without user opt-in or a clearly documented region-specific justification.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/literature_collector.py (reported line 393)May include surrounding context.

python
if ZOTERO_GROUP_ID:
            env["ZOTERO_GROUP_ID"] = ZOTERO_GROUP_ID
        
        result = subprocess.run(
            ["python3", ZOTERO_SCRIPT, "collections", "--json"],
            capture_output=True, text=True, timeout=30, env=env
        )

Tainted flow: 'url' from requests.get (line 479, network input) → requests.get (network output)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/literature_collector.py (reported line 788)May include surrounding context.

python
query = quote(f"((cat:q-bio OR cat:cs.AI OR cat:cs.LG) AND (machine learning OR deep learning OR bioinformatics OR metagenomics)) AND {submitted_date_filter}")
        url = f"http://export.arxiv.org/api/query?search_query={query}&start=0&max_results={max_results}&sortBy=submittedDate&sortOrder=descending"
        
        response = requests.get(url, timeout=30)
        response.raise_for_status()
        
        root = ET.fromstring(response.text)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill's stated purpose is daily literature reporting, but the script also transmits the generated report to Matrix and pushes article metadata into Zotero. That broader data distribution can expose collected content, workspace-derived output, and organizational metadata to external systems without an explicit consent step at the point of transmission.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script sends a full generated report to Matrix and uploads article metadata to Zotero without a clear user-facing warning or confirmation immediately before transmission. In an agent-skill context, silent external sharing increases the chance of unintended disclosure, especially if reports later include user notes, internal commentary, or proprietary research selections.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

L183 明确写明“基于摘要生成 100-250 字中文格式总结”,属于自然语言层面的固定语言要求。文档中未说明这是地区特定场景,也未提供用户选择其他语言或显式 opt-in,因此符合语言/locale policy violation 条件。

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The manifest does not mention credential handling or authenticated third-party integrations; it focuses on literature collection and report generation. Reading ZOTERO_API_KEY and group identifiers adds account/integration capability that is not justified by the declared purpose alone.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The code creates persistent markdown reports and copies them into another workspace directory, which affects user data and filesystem state. While it prints after saving/syncing, there is no upfront disclosure in the script description or near execution entry that running this skill will create and overwrite files in multiple locations.

Content

No source excerpt is available for this finding.