Security Audit
product-manager-toolkit
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
product-manager-toolkit received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary File Read Leading to Data Exfiltration.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 20, 2026 (commit e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Arbitrary File Read Leading to Data Exfiltration The `customer_interview_analyzer.py` script takes a file path as a command-line argument and reads its content without sufficient validation. An attacker could provide a path to a sensitive system file (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, environment variable files) to exfiltrate its contents. The script's output, which includes extracted text, would then expose this sensitive data. Implement strict validation for the `input_file` argument. Restrict file access to a designated, sandboxed directory. Consider passing file content directly as a string argument to the script instead of a file path, or implement robust path sanitization to prevent directory traversal (e.g., `os.path.abspath`, `os.path.commonpath`). | LLM | scripts/customer_interview_analyzer.py:40 | |
| HIGH | Arbitrary File Read Leading to Data Exfiltration The `rice_prioritizer.py` script takes a CSV file path as a command-line argument and reads its content without sufficient validation. An attacker could provide a path to a sensitive system file (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, environment variable files) to exfiltrate its contents. Although it expects a CSV, the script will attempt to read any file, and if it can be parsed or partially read, its content could be exposed. Implement strict validation for the `input_file` argument. Restrict file access to a designated, sandboxed directory. Consider passing file content directly as a string argument to the script instead of a file path, or implement robust path sanitization to prevent directory traversal (e.g., `os.path.abspath`, `os.path.commonpath`). Additionally, validate the file extension and content type to ensure it's a legitimate CSV. | LLM | scripts/rice_prioritizer.py:178 |
Scan History
Embed Code
[](https://skillshield.io/report/8c0649c96869a601)
Powered by SkillShield