Trust Assessment
hextec-arena-recommender received a trust score of 20/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 2 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Skill declares broad 'Bash' execution permission.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 63/100, indicating areas for improvement.
Last analyzed on February 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| 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/crazzies/hextec-arena-recommender/scripts/fetch_recommender.py:20 | |
| CRITICAL | Skill declares broad 'Bash' execution permission The skill's manifest explicitly declares `allowed-tools: Bash`. This grants the host LLM the ability to execute arbitrary shell commands on the system. A malicious prompt could instruct the LLM to perform actions such as data exfiltration (e.g., `cat /etc/passwd`), system modification (e.g., `rm -rf /`), or denial of service. While the `skill.md` provides an example of intended usage, the LLM is not inherently constrained by this example, making the skill highly vulnerable to prompt injection leading to arbitrary command execution. Restrict the skill's permissions to the absolute minimum necessary. If shell execution is required, use a more granular tool that exposes only specific, sandboxed commands, or implement robust input validation and sanitization for all arguments passed to Bash commands to prevent command injection. | LLM | skill.md:1 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'fetch_html'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/crazzies/hextec-arena-recommender/scripts/fetch_recommender.py:20 | |
| MEDIUM | Custom npm registry used for dependencies The `package-lock.json` file specifies `http://mirrors.tencentyun.com/npm/` as the resolved registry for npm packages. Relying on a custom or mirrored package registry instead of the official one introduces a supply chain risk. If this mirror is compromised or serves tampered packages, it could lead to the introduction of malicious code into the skill's dependencies. Configure package managers to use official, trusted registries (e.g., `registry.npmjs.org`). If a custom mirror is necessary, ensure it is thoroughly vetted, secured, and its integrity is regularly verified against official sources. | LLM | references/package-lock.json:5 |
Scan History
Embed Code
[](https://skillshield.io/report/04ec7c1dda27469f)
Powered by SkillShield