Trust Assessment
biorxiv-database received a trust score of 77/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 4 findings: 0 critical, 0 high, 3 medium, and 1 low severity. Key findings include Suspicious import: requests, Network egress to untrusted endpoints, Covert behavior / concealment directives.
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 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| 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 | cli-tool/components/skills/scientific/biorxiv-database/scripts/biorxiv_search.py:10 | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| MEDIUM | Unsanitized output_path in PDF download allows path traversal The `download_pdf` function in `BioRxivSearcher` writes content to a file path specified by the user (`output_path`) without any sanitization or validation. If the `output_path` is derived from untrusted input (e.g., directly from an LLM's generated response or a malicious user), an attacker could provide a path like `../../../../etc/passwd` or `/tmp/malicious.sh`. This could lead to overwriting arbitrary files on the system or placing malicious scripts in sensitive locations, potentially compromising the host system. Implement path sanitization to ensure that `output_path` is restricted to an allowed directory. For example, resolve the path to an absolute path and verify that it starts with a designated safe directory, or use `os.path.basename` if only a filename (not a full path) is expected from user input. A common approach is to prepend a secure base directory to any user-provided filename. | LLM | scripts/biorxiv_search.py:307 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/e253c28cfaed90b1)
Powered by SkillShield