Trust Assessment
knuspr received a trust score of 58/100, 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: 2 critical, 0 high, 1 medium, and 0 low severity. Key findings include Suspicious import: urllib.request, Prompt Injection Attempt in Skill Documentation, Plaintext Credential Storage.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 40/100, 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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection Attempt in Skill Documentation The skill's documentation (`SKILL.md`) contains a section titled 'Critical Rules' that attempts to instruct the host LLM on how to behave (e.g., 'NEVER complete a purchase', 'Always use --json'). This is a direct attempt to manipulate the LLM's instructions, which is explicitly forbidden by the SkillShield meta-prompt for untrusted content. Remove all instructions intended for the host LLM from the skill's documentation. The skill's documentation should only describe the skill's functionality, not dictate the LLM's behavior. | LLM | SKILL.md:21 | |
| CRITICAL | Plaintext Credential Storage The `knuspr_cli.py` script stores the user's email and password in plaintext within the `~/.knuspr_credentials.json` file after a successful login. Although file permissions are set to `0o600`, storing credentials unencrypted on disk is a severe security risk, as it makes them vulnerable to any process or attacker gaining local access to the user's system. Implement secure credential storage. This could involve using an operating system's credential manager (e.g., keyring, macOS Keychain, Windows Credential Manager), encrypting the credentials with a user-provided passphrase, or relying solely on environment variables or short-lived session tokens instead of persistent plaintext storage. | LLM | knuspr_cli.py:180 | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' 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 | skills/lars147/knuspr-cli/knuspr_cli.py:44 |
Scan History
Embed Code
[](https://skillshield.io/report/29a98705ec260b64)
Powered by SkillShield