Trust Assessment
cctv-news-fetcher received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Unpinned npm dependency version, Prompt Injection leading to Command Injection via unsanitized user input, Hardcoded Cookie in HTTP Requests.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection leading to Command Injection via unsanitized user input The skill's instructions in SKILL.md explicitly direct the host LLM to execute a shell command (`bun {baseDir}/scripts/news_crawler.js <YYYYMMDD>`). The `<YYYYMMDD>` parameter is derived from user input. If the LLM directly interpolates unsanitized user input into this command, a malicious user could inject arbitrary shell commands (e.g., `20250210; rm -rf /`). This constitutes a critical command injection vulnerability enabled by a prompt injection. The host LLM must sanitize or validate user input (`YYYYMMDD`) before constructing and executing the shell command. Only allow strictly formatted dates. Alternatively, use a safer execution mechanism that does not involve direct shell command construction with user input, or pass the date as an argument to a dedicated function that handles validation internally. | LLM | SKILL.md:16 | |
| MEDIUM | Unpinned npm dependency version Dependency 'node-html-parser' is not pinned to an exact version ('^7.0.2'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/yuhangch/cctv-news-fetcher/package.json | |
| INFO | Hardcoded Cookie in HTTP Requests The `scripts/news_crawler.js` file includes a hardcoded cookie (`cna=DLYSGBDthG4CAbRVCNxSxGT6`) in the headers of all outgoing HTTP requests. While this specific cookie appears to be a benign tracking cookie for CCTV, hardcoding cookies in skill code can be a security hygiene issue. If this cookie were to become sensitive or if the target domain were compromised, it could pose a minor risk. Review the necessity of sending this specific cookie. If it's not strictly required for functionality, remove it. If it is required, consider if it should be dynamically generated or managed more securely, although for a public tracking cookie, this is less critical. | LLM | scripts/news_crawler.js:17 |
Scan History
Embed Code
[](https://skillshield.io/report/fa8f5ca7a655bfde)
Powered by SkillShield