Trust Assessment
gdocs-markdown received a trust score of 65/100, 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: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Command Injection via unsanitized document title, Supply Chain Risk: Unverified download of `pandoc` binary.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via unsanitized document title The `DOC_TITLE` variable, which can be user-provided as the second argument to the script, is used to construct the `DOCX_FILE` path: `DOCX_FILE="$TMP_DIR/${DOC_TITLE// /_}.docx"`. While spaces are replaced, other shell metacharacters (e.g., `$`, `(`, `)`, `\`, `` ` ``) are not sanitized. If `DOC_TITLE` contains a command substitution like `$(evil_command)`, this command will be executed when `DOCX_FILE` is assigned, leading to arbitrary command execution. Sanitize `DOC_TITLE` to remove or escape all shell metacharacters before using it in a filename. A safer approach would be to generate a unique, random filename for the DOCX file (e.g., using `mktemp`) and use the `DOC_TITLE` only as metadata for `gog drive upload` if it supports a title argument, or to rename the file after upload. If the title must be part of the filename, use a function to strictly sanitize it (e.g., allow only alphanumeric, hyphens, underscores). | LLM | scripts/gdocs-create.sh:56 | |
| HIGH | Supply Chain Risk: Unverified download of `pandoc` binary The script downloads the `pandoc` binary using `wget` from a hardcoded URL (`https://github.com/jgm/pandoc/releases/download/3.1.11/pandoc-3.1.11-linux-amd64.tar.gz`) without any integrity verification (e.g., checksum). This makes the skill vulnerable to supply chain attacks. If the GitHub release is compromised, or if a Man-in-the-Middle (MITM) attack occurs during download, a malicious `pandoc` binary could be installed and executed, leading to arbitrary code execution on the user's system. Implement integrity verification for downloaded binaries. This typically involves downloading a checksum file (e.g., SHA256SUMS) from a trusted source and verifying the downloaded `pandoc` archive against it before extraction and execution. Alternatively, consider packaging `pandoc` with the skill or relying solely on a system-installed version. | LLM | scripts/gdocs-create.sh:44 |
Scan History
Embed Code
[](https://skillshield.io/report/d2c14c549b4d7e85)
Powered by SkillShield