Trust Assessment
travel-destination-brochure 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 15 findings: 3 critical, 8 high, 4 medium, and 0 low severity. Key findings include Arbitrary command execution, Suspicious import: requests, Potential data exfiltration: file read + network send.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 0/100, indicating areas for improvement.
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 Findings15
| 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/mehediahamed/travel-destination-brochure/scripts/run_travel_pipeline.py:24 | |
| 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/mehediahamed/travel-destination-brochure/scripts/simple_travel_brochure.py:162 | |
| 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/mehediahamed/travel-destination-brochure/scripts/simple_travel_brochure.py:195 | |
| HIGH | Potential data exfiltration: file read + network send Function 'download_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/mehediahamed/travel-destination-brochure/scripts/fetch_commons.py:61 | |
| HIGH | Potential data exfiltration: file read + network send Function 'download_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/mehediahamed/travel-destination-brochure/scripts/fetch_openstreetcam.py:36 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_cmd'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/mehediahamed/travel-destination-brochure/scripts/run_travel_pipeline.py:24 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'generate_video'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/mehediahamed/travel-destination-brochure/scripts/simple_travel_brochure.py:162 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'generate_travel_plan'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/mehediahamed/travel-destination-brochure/scripts/simple_travel_brochure.py:195 | |
| HIGH | Potential data exfiltration: file read + network send Function 'download_image' 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/mehediahamed/travel-destination-brochure/scripts/simple_travel_brochure.py:137 | |
| HIGH | Arbitrary directory deletion via output path The `simple_travel_brochure.py` script uses `shutil.rmtree(out_dir, ignore_errors=True)` to clean up previous output. The `out_dir` variable is directly derived from the `--output` command-line argument. If an attacker can control this argument (e.g., by providing `--output /` or `--output ../../`), they could cause the script to delete arbitrary directories on the system where the skill is executed. Implement strict validation for the `--output` argument to ensure it is a relative path within a designated, sandboxed output directory and does not contain path traversal sequences (e.g., `..`). Alternatively, ensure the skill is executed in a highly restricted sandbox environment where file system access is limited. | LLM | scripts/simple_travel_brochure.py:180 | |
| HIGH | Arbitrary file write via output path Multiple scripts (`fetch_commons.py`, `fetch_openstreetcam.py`, `run_travel_pipeline.py`, `simple_travel_brochure.py`) construct output file paths (for images and manifests) based on command-line arguments like `--output` or `--output-dir`. For example, `download_image(url, path)` writes to `path`, where `path` is derived from `args.output`. If an attacker can control these arguments (e.g., by providing `--output /etc` or `--output ../../`), they could cause the scripts to write files to arbitrary locations on the system. While the content is from trusted external APIs (images), overwriting system files could lead to denial of service or other system instability. Implement strict validation for all output path arguments (`--output`, `--output-dir`) to ensure they are relative paths within a designated, sandboxed output directory and do not contain path traversal sequences (e.g., `..`). Alternatively, ensure the skill is executed in a highly restricted sandbox environment where file system write access is limited. | LLM | scripts/simple_travel_brochure.py:136 | |
| 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 | skills/mehediahamed/travel-destination-brochure/scripts/fetch_commons.py:18 | |
| 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 | skills/mehediahamed/travel-destination-brochure/scripts/fetch_openstreetcam.py:16 | |
| 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 | skills/mehediahamed/travel-destination-brochure/scripts/geocode_city.py:16 | |
| 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 | skills/mehediahamed/travel-destination-brochure/scripts/simple_travel_brochure.py:18 |
Scan History
Embed Code
[](https://skillshield.io/report/b7181f3c9dc4d430)
Powered by SkillShield