Trust Assessment
deep-research received a trust score of 11/100, 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, 6 high, 0 medium, and 0 low severity. Key findings include Sensitive path access: AI agent config, Server-Side Request Forgery (SSRF) via SearXNG results, Unpinned Python dependencies.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 25/100, indicating areas for improvement.
Last analyzed on February 13, 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 | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/romancircus/privatedeepsearch-melt/skills/deep-research/SKILL.md:9 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/romancircus/privatedeepsearch-melt/skills/deep-research/SKILL.md:53 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/romancircus/privatedeepsearch-melt/skills/deep-research/SKILL.md:122 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/romancircus/privatedeepsearch-melt/skills/deep-research/SKILL.md:127 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/romancircus/privatedeepsearch-melt/skills/deep-research/SKILL.md:132 | |
| HIGH | Server-Side Request Forgery (SSRF) via SearXNG results The `fetch_content` function makes HTTP requests to URLs returned by the local SearXNG instance. If the SearXNG instance is compromised or misconfigured to return internal network URLs (e.g., `http://localhost:port/admin` or `http://192.168.1.100/sensitive-data`), the skill will attempt to fetch the content from these internal resources and include it in the generated report. This allows an attacker to potentially exfiltrate data from internal services accessible from the skill's execution environment. The `is_valid_url` check does not prevent fetching `localhost` or private IP addresses. Implement stricter URL validation in `is_valid_url` to prevent fetching from `localhost`, private IP ranges, or other internal network addresses. Consider using a whitelist of allowed schemes and hosts, or a blacklist of internal IP ranges. | LLM | deep_research.py:100 | |
| INFO | Unpinned Python dependencies The `Manifest` and `SKILL.md` specify Python dependencies (`aiohttp`, `beautifulsoup4`) without pinning their versions. This can lead to non-deterministic builds and potential security vulnerabilities if a future version of a dependency introduces a breaking change or a security flaw. An attacker could potentially introduce malicious code into a new version of an unpinned dependency. Pin exact versions for all Python dependencies (e.g., `aiohttp==3.8.1`, `beautifulsoup4==4.11.1`) to ensure deterministic and secure installations. Use a `requirements.txt` file with pinned versions. | LLM | SKILL.md:100 |
Scan History
Embed Code
[](https://skillshield.io/report/4e445ea8d12f606a)
Powered by SkillShield