Trust Assessment
pandoc-convert 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 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via CLI arguments.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Potential Command Injection via CLI arguments The skill's core functionality involves executing external command-line tools (pandoc, python scripts, bash scripts) and passing user-controlled input as arguments. The `SKILL.md` describes command interfaces for `convert.py`, `batch_convert.sh`, and `validate.sh` that accept various parameters (e.g., `INPUT`, `OUTPUT`, `FORMAT`, `TEMPLATE`, `FILE`, `OPTIONS`). If these user-supplied arguments are not properly sanitized or escaped before being passed to shell commands (e.g., via `subprocess.run(..., shell=True)` in Python or direct string concatenation in bash), a malicious user could inject arbitrary shell commands, leading to arbitrary code execution on the host system. This is a common vulnerability in wrappers around CLI tools. Ensure all user-supplied arguments passed to `pandoc`, `python`, or `bash` commands are rigorously sanitized and properly escaped. For Python `subprocess` calls, prefer passing arguments as a list (e.g., `subprocess.run(['pandoc', input_file, '-o', output_file])`) and avoid `shell=True`. For bash scripts, use parameter expansion with quoting (e.g., `"$1"`) and validate input to prevent injection of special characters or commands. | LLM | SKILL.md:64 |
Scan History
Embed Code
[](https://skillshield.io/report/7f821d7e01762d41)
Powered by SkillShield