Trust Assessment
grok-image received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 10 findings: 6 critical, 4 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, File read + network send exfiltration, Dangerous call: subprocess.run().
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
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 Findings10
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/raphbaph/grok-imagine-render/scripts/generate_image.py:27 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/raphbaph/grok-imagine-render/scripts/generate_image.py:60 | |
| 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/raphbaph/grok-imagine-render/SKILL.md:6 | |
| 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/raphbaph/grok-imagine-render/SKILL.md:20 | |
| 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/raphbaph/grok-imagine-render/scripts/generate_image.py:46 | |
| CRITICAL | Command Injection via unescaped output path in `curl` command The `output_path` argument, which is directly controlled by the user via the `--output` command-line option, is interpolated into a `curl` command executed with `shell=True`. This allows an attacker to inject arbitrary shell commands by crafting a malicious `output_path` value. For example, providing `--output "/tmp/image.png; rm -rf /"` would execute `rm -rf /` on the system where the skill is run. Avoid `shell=True` when executing external commands with user-controlled input. Instead, pass the command and its arguments as a list to `subprocess.run`. For example: `subprocess.run(["curl", "-s", "-o", output_path, image_url], check=True)`. Alternatively, use a dedicated Python HTTP library (e.g., `requests`) to download the image, eliminating the need for `curl` and `shell=True`. If `shell=True` is strictly required, ensure `output_path` is properly escaped using `shlex.quote()`. | LLM | scripts/generate_image.py:58 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_curl'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/raphbaph/grok-imagine-render/scripts/generate_image.py:27 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'generate_image'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/raphbaph/grok-imagine-render/scripts/generate_image.py:60 | |
| 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/raphbaph/grok-imagine-render/SKILL.md:6 | |
| 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/raphbaph/grok-imagine-render/SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/9dfec068354d7b76)
Powered by SkillShield