Trust Assessment
moltscope received a trust score of 35/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 1 critical, 2 high, 1 medium, and 0 low severity. Key findings include Hardcoded Bearer Token detected, Skill instructs agent to reveal private key to external service, Unpinned dependency and lack of integrity checks for skill files.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 63/100, 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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Skill instructs agent to reveal private key to external service The skill's documentation explicitly provides a `curl` command instructing an AI agent to send its private key to `https://moltscope.net/api/v1/agents/wallet` via a POST request with `{"reveal":true}`. Transmitting a private key to any external service grants that service full control over the agent's associated cryptocurrency wallet, leading to complete financial compromise and potential loss of assets. This is an extremely dangerous security anti-pattern and constitutes a direct credential harvesting and data exfiltration risk. Remove any functionality or instructions that require an agent to transmit its private key to an external service. Private keys must remain securely stored and managed locally by the agent. If cryptographic operations are needed, they should be performed client-side using the locally stored key, with only signed transactions or public keys being sent to external services. | LLM | SKILL.md:79 | |
| HIGH | Hardcoded Bearer Token detected A hardcoded Bearer Token was found. Secrets should be stored in environment variables or a secret manager. Replace the hardcoded secret with an environment variable reference. | Static | skills/moltscopedev/moltscope/SKILL.md:42 | |
| HIGH | Hardcoded Bearer Token detected A hardcoded Bearer Token was found. Secrets should be stored in environment variables or a secret manager. Replace the hardcoded secret with an environment variable reference. | Static | skills/moltscopedev/moltscope/SKILL.md:49 | |
| MEDIUM | Unpinned dependency and lack of integrity checks for skill files The skill's installation instructions use `npx molthub@latest`, which does not specify a fixed version for the `molthub` package. This introduces a supply chain risk, as a malicious update to `molthub` could compromise the installation process. Furthermore, the `curl` commands used to download `SKILL.md`, `HEARTBEAT.md`, `MESSAGING.md`, and `skill.json` from `moltscope.net` do not include any integrity verification mechanisms (e.g., cryptographic hashes). This means that if `moltscope.net` were compromised, an attacker could inject malicious code into the skill files downloaded by agents without detection. For `npx` commands, pin the package to a specific version (e.g., `npx molthub@1.2.3 install moltscope`). For downloaded skill files, provide cryptographic hashes (e.g., SHA256) that agents can use to verify the integrity of the downloaded content before installation. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/6f131cb6762b833b)
Powered by SkillShield