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 22 findings: 8 critical, 13 high, 1 medium, and 0 low severity. Key findings include Covert behavior / concealment directives, Unsafe environment variable passthrough, Arbitrary command execution.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on July 1, 2026 (commit 35414756). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings22
| 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/docx/scripts/accept_changes.py:68 | |
| 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/docx/scripts/accept_changes.py:99 | |
| 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/docx/scripts/office/soffice.py:14 | |
| 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/docx/scripts/office/soffice.py:37 | |
| 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/docx/scripts/office/soffice.py:59 | |
| 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/docx/scripts/office/validators/redlining.py:138 | |
| 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/docx/scripts/office/validators/redlining.py:167 | |
| CRITICAL | Credential harvesting Bulk environment variable dump Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/docx/scripts/office/soffice.py:25 | |
| HIGH | Covert behavior / concealment directives HTML comment containing suspicious keywords Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/docx/SKILL.md:413 | |
| HIGH | Unsafe environment variable passthrough Bulk environment variable harvesting Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/docx/scripts/office/soffice.py:25 | |
| HIGH | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/docx/scripts/comment.py:91 | |
| HIGH | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/docx/scripts/office/pack.py:117 | |
| HIGH | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/docx/scripts/office/validators/pptx.py:207 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'accept_changes'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/docx/scripts/accept_changes.py:68 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function '_setup_libreoffice_macro'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/docx/scripts/accept_changes.py:99 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_soffice'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/docx/scripts/office/soffice.py:37 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function '_ensure_shim'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/docx/scripts/office/soffice.py:59 | |
| 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 | skills/docx/scripts/office/validators/redlining.py:138 | |
| 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 | skills/docx/scripts/office/validators/redlining.py:167 | |
| HIGH | Insecure LD_PRELOAD shared library loading from world-writable /tmp The script defines a static path in the world-writable `/tmp` directory (`/tmp/lo_socket_shim.so`) to compile and load a shared library via `LD_PRELOAD`. Because it reuses the file if it already exists without verifying ownership or integrity, a local attacker can pre-create this file with malicious code, leading to arbitrary code execution when another user runs the script. Use a secure, user-specific temporary directory (e.g., using `tempfile.mkdtemp()`) or include the current user's UID in the filename (e.g., `/tmp/lo_socket_shim_{uid}.so`) and ensure the file is owned by the current user and not writable by others before loading it. | LLM | scripts/office/soffice.py:48 | |
| HIGH | Insecure LibreOffice profile and macro execution from world-writable /tmp The script uses a static path in the world-writable `/tmp` directory (`/tmp/libreoffice_docx_profile`) for the LibreOffice user profile. It checks if the macro file `Module1.xba` exists and contains the string 'AcceptAllTrackedChanges' before reusing it. A local attacker can pre-create this macro file with malicious Basic code containing the required string, leading to arbitrary code execution when LibreOffice executes the macro. Use a secure, user-specific temporary directory for the LibreOffice profile (e.g., using `tempfile.mkdtemp()`) to prevent other users from pre-creating or modifying the profile and macro files. | LLM | scripts/accept_changes.py:16 | |
| MEDIUM | Suspicious import: socket Import of 'socket' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/docx/scripts/office/soffice.py:18 |
Scan History
Embed Code
[](https://skillshield.io/report/6afc76a2cb0af36b)
Powered by SkillShield