Trust Assessment
undetectable-ai received a trust score of 66/100, 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: 0 critical, 2 high, 1 medium, and 0 low severity. Key findings include Unpinned npm dependency version, Arbitrary File Read via Command Line Argument, Arbitrary File Write via Command Line Argument.
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 13, 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 | |
|---|---|---|---|---|
| HIGH | Arbitrary File Read via Command Line Argument The `analyze.ts` and `transform.ts` scripts read file paths provided as command-line arguments without validation or restriction. This allows the skill to read any file accessible to the agent's execution environment. An attacker could exploit this to exfiltrate sensitive data by providing paths to system files (e.g., `/etc/passwd`, API keys, configuration files) and having their content processed and potentially returned in the skill's output. The skill declares 'Read' permission, but the scope of access is overly broad. Implement strict validation for input file paths to ensure they are within expected directories or adhere to a whitelist of allowed file types. Avoid reading arbitrary paths from untrusted input. If broad file access is necessary, ensure robust sandboxing or user consent mechanisms are in place. | LLM | scripts/analyze.ts:60 | |
| HIGH | Arbitrary File Write via Command Line Argument The `transform.ts` script writes to an output file path provided as a command-line argument without validation or restriction. This allows the skill to write to any file accessible to the agent's execution environment. An attacker could exploit this to overwrite critical system files, configuration files, or logs, leading to data tampering, denial of service, or other system instability. While the content written is transformed text, overwriting system files with any content can cause significant damage. The skill declares 'Write' permission, but the scope of access is overly broad. Implement strict validation for output file paths to ensure they are within expected output directories or temporary locations. Prevent writing to sensitive system paths. If broad file write access is necessary, ensure robust sandboxing or user consent mechanisms are in place. | LLM | scripts/transform.ts:127 | |
| MEDIUM | Unpinned npm dependency version Dependency '@types/node' is not pinned to an exact version ('^20.0.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/artur-zhdan/undetectable-ai/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/7c98ef59ecd80335)
Powered by SkillShield