Trust Assessment
coloring-page received a trust score of 28/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 2 critical, 1 high, 0 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Potential Command Injection via unsanitized file paths.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/borahm/coloring-page/SKILL.md:15 | |
| CRITICAL | Potential Command Injection via unsanitized file paths The skill's instructions in `SKILL.md` specify running `bin/coloring-page` with user-provided input (`--in <path-to-uploaded-image>`) and optional output (`--out <output.png>`) file paths. If the assistant or the `bin/coloring-page` script does not properly sanitize or quote these user-controlled paths before executing the command, an attacker could inject arbitrary shell commands. For example, an image file named `"; rm -rf /tmp/*; #.jpg"` could lead to critical system compromise. Additionally, the `--out` parameter could be exploited for path traversal (e.g., `../../../etc/passwd`) leading to arbitrary file writes. 1. **Assistant-side:** Ensure all user-provided arguments passed to shell commands are properly escaped and quoted. For example, use `shlex.quote()` in Python or similar mechanisms in other languages to prevent shell metacharacter interpretation. 2. **Skill-side:** The `bin/coloring-page` script should implement robust validation and sanitization for all input arguments, especially file paths. It should prevent path traversal attempts and avoid directly interpolating paths into sub-shell commands without proper escaping. Prefer using safe file system APIs. | LLM | SKILL.md:29 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/borahm/coloring-page/SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/bb04de54222dd2c4)
Powered by SkillShield