Trust Assessment
openclaw-media-gen received a trust score of 64/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 2 high, 1 medium, and 0 low severity. Key findings include Suspicious import: urllib.request, Potential data exfiltration: file read + network send, Arbitrary File Write via User-Controlled Path.
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 | |
|---|---|---|---|---|
| HIGH | Potential data exfiltration: file read + network send Function '_download_to_file' reads files and sends data over the network. This may indicate data exfiltration. Review this function to ensure file contents are not being sent to external servers. | Static | skills/0xjordansg-yolo/openclaw-aisa-image-video-models-wan2-6-gemini-3-pro-image-nano-banana/scripts/media_gen_client.py:93 | |
| HIGH | Arbitrary File Write via User-Controlled Path The skill's Python client (`scripts/media_gen_client.py`) allows writing files to arbitrary paths specified by the `--out` argument. This is present in both the `image` generation command and the `video-wait` command when `--download` is used. An attacker could craft a malicious prompt to the host LLM, instructing it to call this skill with a path traversal sequence (e.g., `../../sensitive_file`) or an absolute path (e.g., `/etc/cron.d/malicious_job`), leading to overwriting or creating files in sensitive system locations. This could be escalated to command injection or system compromise depending on the target file and execution context. Sanitize the `--out` argument to prevent path traversal (e.g., using `os.path.basename` if only a filename is expected, or `pathlib.Path.name`). Alternatively, restrict file output to a designated, non-sensitive subdirectory within the skill's working directory, ensuring all output paths are prefixed with this safe directory and validated. | LLM | scripts/media_gen_client.py:107 | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' 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 | skills/0xjordansg-yolo/openclaw-aisa-image-video-models-wan2-6-gemini-3-pro-image-nano-banana/scripts/media_gen_client.py:24 |
Scan History
Embed Code
[](https://skillshield.io/report/de1e05191770fb78)
Powered by SkillShield