Trust Assessment
knowledge-graph received a trust score of 85/100, 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 Potential Command Injection via Unsanitized Entity Slugs.
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 August 1, 2026 (commit a4d31ad1). 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 | Potential Command Injection via Unsanitized Entity Slugs The skill requests 'exec' permissions to run local filesystem commands for creating entity folders based on 'slugs' resolved from conversation history or recent work. If the agent constructs shell commands (e.g., 'mkdir -p life/areas/people/<slug>') using these dynamically resolved slugs without strict sanitization, an attacker could inject shell metacharacters (e.g., ';', '`', '$()') into a conversation to trigger arbitrary command execution. Avoid using shell commands ('exec') to create directories. Instead, use safer filesystem APIs (such as Node's 'fs.mkdir' or Python's 'os.makedirs') that do not invoke a shell. If shell commands must be used, strictly validate and sanitize the 'slug' to allow only alphanumeric characters and hyphens. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/d25cc0dfa826a287)
Powered by SkillShield