Trust Assessment
docx 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 12 findings: 3 critical, 6 high, 2 medium, and 1 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Network egress to untrusted endpoints.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 1/100, indicating areas for improvement.
Last analyzed on February 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings12
| 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 | cli-tool/components/skills/document-processing/docx/ooxml/scripts/pack.py:103 | |
| 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 | cli-tool/components/skills/document-processing/docx/ooxml/scripts/validation/redlining.py:153 | |
| 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 | cli-tool/components/skills/document-processing/docx/ooxml/scripts/validation/redlining.py:185 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'validate_document'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/document-processing/docx/ooxml/scripts/pack.py:103 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function '_get_git_word_diff'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/document-processing/docx/ooxml/scripts/validation/redlining.py:153 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function '_get_git_word_diff'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | cli-tool/components/skills/document-processing/docx/ooxml/scripts/validation/redlining.py:185 | |
| HIGH | Zip Slip Vulnerability in File Unpacking The `unpack.py` script uses `zipfile.ZipFile(input_file).extractall(output_path)` where `input_file` is directly taken from user input (`sys.argv[1]`). The `extractall` method does not sanitize filenames, making it vulnerable to Zip Slip attacks. A malicious `.docx` file could contain entries with path traversal sequences (e.g., `../../malicious.txt`), allowing an attacker to write arbitrary files outside the intended `output_dir` on the filesystem. Before extracting, validate each member's filename within the zip archive to ensure it does not contain path traversal sequences. A common approach is to resolve the full path of each member and verify that it remains within the designated `output_path`. | Static | ooxml/scripts/unpack.py:13 | |
| HIGH | Zip Slip Vulnerability in Validation Unpacking The `redlining.py` script uses `zipfile.ZipFile(self.original_docx, 'r').extractall(temp_path)` to unpack the original document for validation. While `temp_path` is a temporary directory, `self.original_docx` is derived from user input. This still presents a Zip Slip vulnerability, as a malicious `.docx` could write files outside `temp_path` (e.g., to `/tmp` or other accessible locations), potentially interfering with other processes or leaving malicious artifacts. Implement path sanitization for each member extracted from the zip archive. Ensure that the resolved path of each extracted file is strictly confined to the `temp_path` directory to prevent writing to arbitrary locations on the filesystem. | Static | ooxml/scripts/validation/redlining.py:67 | |
| HIGH | LLM analysis found no issues despite critical deterministic findings Deterministic layers flagged 3 CRITICAL findings, but LLM semantic analysis returned clean. This may indicate prompt injection or analysis evasion. | LLM | (sanity check) | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| MEDIUM | Unpinned Dependency Installation The skill instructs the installation of `docx` via `npm install -g docx` and `defusedxml` via `pip install defusedxml` without specifying a version. This can lead to supply chain vulnerabilities if a malicious version of the package is published or if future versions introduce breaking changes or security flaws. It also applies to system packages like `pandoc`, `libreoffice`, and `poppler-utils`. Specify exact versions for all dependencies (e.g., `npm install -g docx@x.y.z`, `pip install defusedxml==x.y.z`) to ensure deterministic and secure installations. For system packages, consider using a specific version or ensuring the environment is controlled. | Static | SKILL.md:136 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/7643b37c23cddd31)
Powered by SkillShield