Trust Assessment
rdkit received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 5 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, User-controlled output file path.
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 Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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 | |
| 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 | |
| INFO | User-controlled output file path The script allows a user to specify an arbitrary output file path via command-line arguments. While the content written to these files is structured (CSV, SMILES, or SDF) and derived from molecular data, not arbitrary user input, an attacker could potentially use this to overwrite or append data to sensitive system files if the execution environment grants sufficient write permissions. This is a common pattern for command-line utilities, but it's important to be aware of the potential for misuse in an unsandboxed environment. Ensure that the execution environment for these scripts is properly sandboxed, restricting write access to only designated output directories. If the script is exposed to untrusted input, validate and sanitize file paths to prevent writing to arbitrary or sensitive locations (e.g., restrict to a specific output directory, disallow absolute paths, or paths containing '..'). | Static | scripts/molecular_properties.py:128 | |
| INFO | User-controlled output file path The script allows a user to specify an arbitrary output file path via command-line arguments. While the content written to these files is structured (CSV, SMILES, or SDF) and derived from molecular data, not arbitrary user input, an attacker could potentially use this to overwrite or append data to sensitive system files if the execution environment grants sufficient write permissions. This is a common pattern for command-line utilities, but it's important to be aware of the potential for misuse in an unsandboxed environment. Ensure that the execution environment for these scripts is properly sandboxed, restricting write access to only designated output directories. If the script is exposed to untrusted input, validate and sanitize file paths to prevent writing to arbitrary or sensitive locations (e.g., restrict to a specific output directory, disallow absolute paths, or paths containing '..'). | Static | scripts/similarity_search.py:160 | |
| INFO | User-controlled output file path The script allows a user to specify an arbitrary output file path via command-line arguments. While the content written to these files is structured (CSV, SMILES, or SDF) and derived from molecular data, not arbitrary user input, an attacker could potentially use this to overwrite or append data to sensitive system files if the execution environment grants sufficient write permissions. This is a common pattern for command-line utilities, but it's important to be aware of the potential for misuse in an unsandboxed environment. Ensure that the execution environment for these scripts is properly sandboxed, restricting write access to only designated output directories. If the script is exposed to untrusted input, validate and sanitize file paths to prevent writing to arbitrary or sensitive locations (e.g., restrict to a specific output directory, disallow absolute paths, or paths containing '..'). | Static | scripts/substructure_filter.py:158 |
Scan History
Embed Code
[](https://skillshield.io/report/4036b6748d2bc02a)
Powered by SkillShield