Trust Assessment
generate-image received a trust score of 68/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 4 findings: 0 critical, 1 high, 2 medium, and 1 low severity. Key findings include Suspicious import: requests, Network egress to untrusted endpoints, Covert behavior / concealment directives.
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 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Arbitrary File Read and Exfiltration via User-Controlled Path The `load_image_as_base64` function reads the content of a file specified by the user via the `--input` argument. This content is then base64 encoded and sent to the OpenRouter API as part of the image editing request. The function does not validate the file type or restrict the file path, allowing a malicious user to specify a path to any file the script has read access to (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, `/proc/self/environ`). The content of such sensitive files would then be exfiltrated to the OpenRouter service. Implement robust validation for the `input_image` path. This should include: 1. **File Type Validation**: Verify that the file is indeed an image by checking its magic bytes, not just the extension. 2. **Path Sanitization**: Restrict the input path to prevent directory traversal (e.g., `../`, absolute paths outside a designated safe directory). 3. **Size Limits**: Implement a maximum file size to prevent denial-of-service or excessive data transfer. 4. **User Warning**: Clearly inform users about the implications of providing file paths and advise against using sensitive files. | Static | scripts/generate_image.py:40 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | cli-tool/components/skills/scientific/generate-image/scripts/generate_image.py:96 | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/e6a974e6f8d2a62a)
Powered by SkillShield