Trust Assessment
Article Illustrator received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Unrestricted Configuration Loading from User Home Directory.
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 | |
|---|---|---|---|---|
| HIGH | Unrestricted Configuration Loading from User Home Directory The skill explicitly states it loads custom configurations from `.article-illustrator/EXTEND.md` (project level) and `$HOME/.config/article-illustrator/EXTEND.md` (user level). This allows an attacker to place a malicious `EXTEND.md` file in a user's home or project directory to control skill behavior. Specifically, the `output directory` setting, if not strictly validated and sandboxed, could be manipulated to write generated files to arbitrary locations on the filesystem, potentially leading to data corruption, overwriting sensitive system files (if permissions allow), or data exfiltration if the specified path is an attacker-controlled network share or URL that triggers external fetches. The `custom styles` setting could also introduce risks if it allows for arbitrary code execution or fetching of untrusted external resources. Implement strict validation and sanitization for all configuration values loaded from `EXTEND.md`, especially `output directory` and `custom styles`. Restrict `output directory` to a sandboxed, skill-specific location that is relative to the article's path or a designated safe output folder. Ensure `custom styles` do not allow arbitrary code execution or external resource fetching without explicit user consent and strict URL validation. Consider implementing a mechanism to verify the integrity of `EXTEND.md` files (e.g., signing or hashing) to prevent tampering. | LLM | SKILL.md:171 |
Scan History
Embed Code
[](https://skillshield.io/report/41f98e60e3da8693)
Powered by SkillShield