Trust Assessment
catbox-upload received a trust score of 30/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 7 findings: 0 critical, 3 high, 4 medium, and 0 low severity. Key findings include Missing required field: name, 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 56/100, 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 Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential data exfiltration: file read + network send Function 'upload_to_catbox' 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/microck/catbox-upload/upload.py:16 | |
| HIGH | Potential data exfiltration: file read + network send Function 'upload_to_litterbox' 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/microck/catbox-upload/upload.py:33 | |
| HIGH | Arbitrary File Upload via User-Controlled Path The skill allows users to specify an arbitrary file path (`args.file`) which is then opened and uploaded to an external service. If the skill is executed with broad filesystem permissions, a malicious actor could instruct it to upload sensitive files (e.g., configuration files, private keys) from the host system, leading to data exfiltration. The `Path(args.file)` constructor does not sanitize or restrict the provided path, making it vulnerable to path traversal or direct access to sensitive files. Implement strict path validation and sandboxing. Restrict the skill's filesystem access to only explicitly allowed directories (e.g., a temporary upload directory). If possible, use a file picker UI instead of raw path input. If raw path input is necessary, validate that the path is within an allowed directory and does not contain directory traversal sequences (e.g., `../`). | LLM | upload.py:59 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/microck/catbox-upload/SKILL.md:1 | |
| 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/microck/catbox-upload/upload.py:7 | |
| MEDIUM | Unpinned Python dependency version Requirement 'requests>=2.31.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/microck/catbox-upload/requirements.txt:1 | |
| MEDIUM | Unpinned 'requests' dependency The `requirements.txt` file specifies `requests>=2.31.0`. This uses a minimum version specifier rather than a fully pinned version (`==`). This means that future installations could pull in a newer version of the `requests` library that might contain vulnerabilities or breaking changes, introducing a supply chain risk. It's best practice to pin dependencies to exact versions for deterministic builds and security. Pin the dependency to an exact version (e.g., `requests==2.31.0`) to ensure deterministic builds and prevent unexpected vulnerabilities from new versions. Regularly review and update pinned dependencies. | LLM | requirements.txt:1 |
Scan History
Embed Code
[](https://skillshield.io/report/e840beb98e28fb83)
Powered by SkillShield