Trust Assessment
trending-skills-monitor received a trust score of 88/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Suspicious import: requests, Data Exfiltration via User-Provided JSON Config File.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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/snail3d/clawd/trending-skills-monitor-skill/scripts/clawdhub_api.py:14 | |
| MEDIUM | Data Exfiltration via User-Provided JSON Config File The skill loads configuration from a user-specified JSON file via the `--config FILE` argument. If an attacker can control the `FILE` path to point to a sensitive file (e.g., `/etc/passwd`, `/root/.ssh/id_rsa`), and that file happens to be valid JSON, its contents could be loaded into the skill's configuration. If the skill is then run in verbose mode (`--verbose`), the parsed values (e.g., `interests`) from this sensitive file would be printed to `stderr`, potentially exfiltrating data. 1. **Input Validation**: Restrict the `--config` path to a specific, non-sensitive directory (e.g., `~/.config/trending-skills-monitor/`) or validate that the path is within expected boundaries. 2. **Sanitization**: Ensure that any data loaded from a user-provided config file is not directly printed or used in a way that could lead to exfiltration, even if it's valid JSON. For example, redact sensitive-looking strings in verbose output. 3. **Least Privilege**: If possible, run the skill with minimal file system access to prevent reading arbitrary files. | LLM | scripts/monitor.py:47 |
Scan History
Embed Code
[](https://skillshield.io/report/b4f5bddf2a1c37d7)
Powered by SkillShield