Back to skill

Security audit

screen reviewer

Security checks for vulnerabilities and agentic risk

Overview

This screen-monitoring skill is purpose-aligned but needs Review because it captures and OCRs full-screen activity, stores sensitive history, and can send derived screen content to AI providers without strong consent, redaction, or scoping controls.

Install only if you intentionally want continuous screen monitoring. Review and narrow the app blacklist, consider disabling OCR, avoid cloud AI providers for sensitive work unless you accept sending window titles and OCR samples off-device, and check the ~/.screen-reviewer directory regularly because logs and reports can preserve sensitive content indefinitely.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (5)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/report_generator.py:211
Finding

Sensitive OCR Content and Window Metadata Are Transmitted to External AI Providers Without Redaction

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/capture_daemon.py:123
Finding

Foreground-Application Blacklist Does Not Prevent Sensitive Content Elsewhere on the Screen from Being Captured

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/report_generator.py:48
Finding

Untrusted OCR Text and Window Titles Are Sent to the Language Model Without Prompt-Injection Controls

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
scripts/requirements.txt:1
Finding

Dependency Installation Uses Unbounded Version Ranges Without Hash Verification

Content
View full analysis
=10.0.0 PyYAML>=6.0 openai>=1.0.0 anthropic>=0.20.0 ``` ```bash if [ ! -d "$VENV_DIR" ]; then python3 -m venv "$VENV_DIR" fi source "$VENV_DIR/bin/activate" pip install --upgrade pip -q pip install -r "$REPO_DIR/scripts/requirements.txt" -q ``` ### Technical Analysis All dependencies use lower-bound-only constraints. Future releases, including major versions with incompatible or compromised behavior, automatically satisfy these constraints. The installer also upgrades `pip` to the newest available version each time it runs. No lockfile, artifact hashes, package index restriction, or integrity verification is used. Installation therefore depends entirely on the current state of the configured Python package index and its transitive dependency graph. There is no evidence that the named packages are currently malicious. The vulnerability is the absence of reproducible and integrity-checked dependency resolution for software that handles highly sensitive screenshot and OCR data. ### Attack Path 1. A direct or transitive dependency account, release process, or package-index distribution channel is compromised. 2. A malicious version is published that satisfies one of the `>=` constraints. 3. A user runs `install.sh` or reinstalls dependencies. 4. `pip` resolves and installs the malicious release without a hash mismatch or version-lock failure. 5. Malicious package code runs when imported by the capture or report process. 6. The package inherits the current user's access, including access to screenshots, OCR logs, API keys present in the environment, and Screen Recording-authorized workflows. ### Impact Assessment A compromised dependency can execute code as the current user, read or alter all Skill data, access provider crede ...[truncated 282 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/capture_daemon.py:101
Finding

Screenshots and OCR Logs Are Stored in Plaintext Without Enforced Restrictive Permissions or Complete Retention Controls

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
Findings (80)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

This skill enables periodic screenshot capture, OCR extraction, structured activity logging, and AI-generated reports, but the instructions shown do not present a clear upfront privacy warning about the sensitivity of the collected data or that it may be sent to a third-party AI provider. Users may unknowingly expose credentials, personal messages, confidential documents, or regulated data visible on screen, making the omission materially dangerous in a screen-monitoring context.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation describes the tool as a screen review assistant but does not prominently warn that it performs automatic screenshots, OCR extraction, and local retention of potentially sensitive on-screen content. This creates a meaningful privacy and security risk because users may enable continuous monitoring without informed consent, leading to capture of credentials, personal messages, proprietary data, or regulated information.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README promotes continuous screenshots, OCR, and permanent retention of logs/reports, but it does not clearly warn that highly sensitive data may be captured, extracted, and stored, including passwords, private messages, financial information, or confidential work content. In a screen-monitoring skill, this omission is especially dangerous because users may enable broad collection with only a vague 'privacy protection' assurance and underestimate the scope and persistence of the surveillance data.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README instructs users to configure OpenAI/Anthropic/Ollama for report generation but does not clearly disclose that screen-derived OCR text, activity logs, or summaries may be transmitted to third-party AI providers. Because this skill processes screen contents, the exported data may include sensitive personal, corporate, regulated, or credential-related information, creating a serious confidentiality and compliance risk.

Content

No source excerpt is available for this finding.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.md (reported line 152)May include surrounding context.

bash
bash uninstall.sh
# 如需彻底删除数据:rm -rf ~/.screen-reviewer

License

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.md (reported line 152)May include surrounding context.

bash
bash uninstall.sh
# 如需彻底删除数据:rm -rf ~/.screen-reviewer

License

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill advertises local monitoring and review generation, but the configuration explicitly supports sending activity-derived data to external AI providers such as OpenAI or Anthropic. Failing to clearly disclose external transmission is dangerous because screenshots, OCR text, app names, and window titles may contain credentials, private messages, client data, or regulated information.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The skill advertises local monitoring and review generation, but the configuration explicitly supports sending activity-derived data to external AI providers such as OpenAI or Anthropic. Failing to clearly disclose external transmission is dangerous because screenshots, OCR text, app names, and window titles may contain credentials, private messages, client data, or regulated information.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill advertises local monitoring and review generation, but the configuration explicitly supports sending activity-derived data to external AI providers such as OpenAI or Anthropic. Failing to clearly disclose external transmission is dangerous because screenshots, OCR text, app names, and window titles may contain credentials, private messages, client data, or regulated information.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill advertises local monitoring and review generation, but the configuration explicitly supports sending activity-derived data to external AI providers such as OpenAI or Anthropic. Failing to clearly disclose external transmission is dangerous because screenshots, OCR text, app names, and window titles may contain credentials, private messages, client data, or regulated information.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The markdown does not provide a clear, prominent warning that the skill captures periodic screenshots, extracts text from them, stores logs locally, and may transmit report data to external AI providers. Because screen contents routinely include secrets, personal data, and confidential business information, insufficient disclosure and consent around this collection pipeline is a severe privacy and data-exposure risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The daemon continuously captures full-screen images, extracts OCR text, and stores both screenshots and structured activity logs, which can include highly sensitive information such as messages, credentials, documents, and other personal data. In the context of a screen-monitoring skill, this is especially dangerous because the collection is broad, persistent, and backgrounded, while the code shown provides no visible consent flow, notice, minimization, encryption, or retention controls.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/config.py (reported line 23)May include surrounding context.

python
"change_threshold": 5,  # 至少 N% 像素变化才算"屏幕有变化"
    },
    "privacy": {
        "blacklist_apps": ["1Password", "Keychain Access", "密码"],
    },
    "ocr": {
        "enabled": True,

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The report payload includes app names, window titles, timelines, and OCR-derived content samples, then transmits them to external AI services without any visible warning, consent check, or sanitization. Because this skill monitors screens, the context makes this especially dangerous: the data likely includes private communications, proprietary work product, and other sensitive on-screen content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Listing disk paths for screenshots, logs, and reports without an adjacent sensitivity warning normalizes retention of highly sensitive artifacts and may cause users to overlook that these locations can contain full-screen captures, OCR text, and behavioral summaries. If the host is shared, backed up, synced, or compromised, these files may expose confidential information far beyond ordinary application logs.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill invokes shell commands, reads and writes files under the user's home directory, accesses environment variables for API keys, and can transmit data to external AI providers, yet it declares no explicit tool scope or permission boundaries. For a skill that captures screenshots and OCR text, missing scope declarations materially increases the risk of overbroad access and silent collection or exfiltration of sensitive data.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough that the skill could activate for generic productivity, time tracking, or review requests without the user specifically intending to enable screen surveillance. In the context of a tool that captures screenshots and OCR text, overbroad activation increases the chance of accidental monitoring and collection of highly sensitive information.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description uses very broad trigger language such as general requests about productivity analysis, time tracking, activity logging, and daily review, which can overlap with many benign everyday user prompts. This increases the chance the skill is invoked in contexts broader than intended, potentially enabling unnecessary screenshot monitoring or OCR-based review of sensitive on-screen information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The installer unconditionally deletes whatever exists at the target skill paths with rm -rf before recreating symlinks. If those paths already contain a real directory, prior skill content, or user-managed files, running the installer will silently destroy them, causing data loss and potentially breaking other agent tooling. In this screen-monitoring skill context, the behavior is more concerning because the package asks for persistent installation and autostart-style integration, so users may run it with elevated trust and overlook the destructive side effect.

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/capture_daemon.py (reported line 39)May include surrounding context.

python
def take_screenshot(output_path: str) -> bool:
    """调用 macOS screencapture 截取全屏,保存为 JPEG"""
    try:
        subprocess.run(
            ["screencapture", "-x", "-t", "jpg", output_path],
            capture_output=True, timeout=10,
        )

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/capture_daemon.py (reported line 70)May include surrounding context.

python
return frontApp & "|||" & winTitle
    '''
    try:
        r = subprocess.run(
            ["osascript", "-e", script],
            capture_output=True, text=True, timeout=5,
        )

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring and function docstring are written only in Chinese, which imposes a single language on users and operators without any opt-in or alternative locale support. The policy for natural-language content applies to code comments and string literals as well, so this is a language-policy issue in this file.

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/ocr_processor.py (reported line 36)May include surrounding context.

python
if not os.path.isfile(OCR_BINARY):
        return None
    try:
        result = subprocess.run(
            [OCR_BINARY, image_path],
            capture_output=True, text=True, timeout=15,
        )

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This file hard-codes the OCR languages to chi_sim+eng, which imposes a specific language/locale choice on all users. The stated policy forbids forcing a specific language without user opt-in, and there is no visible parameter, prompt, or documented justification in this file.

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/ocr_processor.py (reported line 64)May include surrounding context.

python
if not os.path.isfile(swift_src):
        return False
    try:
        result = subprocess.run(
            ["swiftc", "-O", "-o", OCR_BINARY, swift_src],
            capture_output=True, text=True, timeout=120,
        )