Astro Natal Chart

• Outcome: Review
• Latest audit: Jun 24, 2026 · 7:27 PM UTC
• Version: 4.3.7

Overview

The skill mostly matches its astrology-chart purpose, but it can automatically install a Python package at runtime and saves personal birth-chart details without strong privacy controls.

Install only if you are comfortable with a Windows-only skill that uses a bundled native astrology library and may install Pillow automatically if it is missing. Treat names, birth dates, exact times, locations, generated PNGs, and exported JSON as personal data, especially before sharing them with an AI service or saving them in synced folders.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

try:
    from PIL import Image, ImageDraw, ImageFont
except ImportError:
    subprocess.check_call([sys.executable,"-m","pip","install","pillow","-q"])
    from PIL import Image, ImageDraw, ImageFont

_ttf_dir = os.path.dirname(os.path.abspath(__file__))

• Confidence: 97% confidence
• Finding: The script automatically runs pip install at runtime if Pillow is missing, which causes network access and arbitrary package installation during normal execution. This is dangerous because package resolution and installation execute untrusted external code in the current environment without user consent, expanding the attack surface well beyond the stated chart-rendering purpose.

Context-Inappropriate Capability

Medium

• Confidence: 98% confidence
• Finding: Installing a Python package at runtime is not necessary for a rendering script and introduces supply-chain risk, unexpected network behavior, and code execution via package installation hooks. In an agent skill context, this is more dangerous because the skill may run in an automation environment where users do not expect dependency changes or outbound installs.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The documented AI workflow encourages sending natal chart JSON containing birth date, time, place, coordinates, and timezone to an AI system without any privacy warning or minimization guidance. This is sensitive personal data, and disclosure to third-party models or logs can expose users to privacy harm, profiling, or unintended retention.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The documentation indicates that output filenames include a person's name and that charts include birth date, time, place, coordinates, and timezone, but it does not warn that this sensitive personal data will be written to local PNG files. This creates a privacy and data-handling risk because users may unknowingly persist identifiable and highly sensitive birth data to disk where it can be indexed, synced, shared, or recovered later.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: Automatically invoking pip without warning or consent is unsafe because it changes the local environment and may execute code retrieved from external package sources. In a skill setting, this violates least surprise and can be abused through dependency confusion, malicious mirrors, or compromised packages.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical

• Code: suspicious.dynamic_code_execution
• Location: scripts/natal_chart_swe.py:41