Trust Assessment
news-aggregator-skill received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via Keyword Expansion.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Keyword Expansion The skill explicitly instructs the LLM to execute `python3 scripts/fetch_news.py` with arguments, including `--keyword`. The `--keyword` argument is explicitly stated to be automatically expanded by the LLM based on user input. If the LLM's keyword expansion or the user's initial input contains shell metacharacters (e.g., `'; rm -rf /'`), and the `fetch_news.py` script does not properly sanitize its arguments before using them in a shell context (e.g., `subprocess.run(shell=True)` or `os.system()`), an attacker could inject arbitrary shell commands. This creates a credible exploit path for command injection. 1. Implement robust input validation and sanitization for all user-provided and LLM-generated arguments, especially for `--keyword`, before passing them to `fetch_news.py`. 2. Ensure `fetch_news.py` uses safe methods for executing external commands (e.g., `subprocess.run` with `shell=False` and passing arguments as a list) to prevent shell injection. 3. Implement LLM guardrails to prevent the generation of malicious shell metacharacters in expanded keywords. | LLM | SKILL.md:28 |
Scan History
Embed Code
[](https://skillshield.io/report/e6910d81767cb232)
Powered by SkillShield