Trust Assessment
word-reader received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 7 findings: 3 critical, 3 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Arbitrary file overwrite via user-controlled output path.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/xtfnhcyjpgf/word-reader/scripts/read_word.py:69 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/xtfnhcyjpgf/word-reader/scripts/read_word.py:75 | |
| CRITICAL | Arbitrary file overwrite via user-controlled output path The `scripts/read_word.py` script allows users to specify an arbitrary file path for output using the `--output` argument. This enables an attacker to overwrite any file on the system that the skill has write permissions to, by directing the processed document content to a sensitive file (e.g., `/etc/passwd`, `/root/.ssh/authorized_keys`). Implement strict validation and sanitization for `output_path`. Restrict output to a designated, sandboxed directory (e.g., a temporary directory or a user-specific output folder). Do not allow arbitrary file paths. Consider using a file picker or explicit user confirmation for sensitive output locations. | LLM | scripts/read_word.py:202 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'read_doc'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/xtfnhcyjpgf/word-reader/scripts/read_word.py:69 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'read_doc'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/xtfnhcyjpgf/word-reader/scripts/read_word.py:75 | |
| HIGH | Arbitrary file read and potential data exfiltration The skill's primary function is to read a user-specified Word document (`file_path` argument). While it checks for `.docx` or `.doc` extensions, an attacker could potentially provide a path to a sensitive non-Word file (e.g., `/etc/passwd`, `/root/.bashrc`) or a symlink to such a file. The script would then attempt to process this file, and its content (or a processed version) would be returned to the calling LLM, enabling data exfiltration. Even if the extension check is robust, the ability to read *any* file within the allowed extensions from *any* location on the filesystem is an excessive permission. Restrict the `file_path` argument to a designated, sandboxed input directory. Implement robust path sanitization to prevent directory traversal attacks (e.g., `../`). If the skill is intended to read user-uploaded files, ensure they are stored in an isolated, non-system-critical location. | LLM | scripts/read_word.py:30 | |
| MEDIUM | Unpinned Python dependency in installation The `install.sh` script and the manifest specify `pip3 install python-docx` without a version specifier. This means that during installation, the latest available version of `python-docx` will be installed. This can lead to unexpected behavior, breaking changes, or the introduction of new vulnerabilities if a future version of the library contains issues. Pin the version of `python-docx` to a known good version (e.g., `python-docx==0.8.11`) in a `requirements.txt` file and install from that file. This ensures deterministic installations and reduces the risk of supply chain attacks or unexpected changes. | LLM | install.sh:66 |
Scan History
Embed Code
[](https://skillshield.io/report/61082599e655d30d)
Powered by SkillShield