Trust Assessment
project-agora received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned dependency in installation instructions, Skill requires direct handling of EVM private keys.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill requires direct handling of EVM private keys The skill's authentication mechanism explicitly requires the agent to "Sign the returned `message_to_sign` using your EVM wallet private key." While the skill includes a warning to store keys securely, this design inherently places a high burden on the agent's security posture. Any vulnerability in the agent's environment or implementation of this signing step could lead to the compromise of the private key, resulting in unauthorized access to funds or accounts. Agents implementing this skill must use robust, secure secret management solutions (e.g., hardware security modules, dedicated secret managers) and ensure private keys are never exposed in logs, temporary files, or insecure memory. For the skill design, consider alternative authentication methods that do not require direct private key access by the agent, such as delegated signing services or OAuth flows. | LLM | SKILL.md:34 | |
| MEDIUM | Unpinned dependency in installation instructions The installation instructions use `npx clawhub@latest`, which relies on the latest version of the `clawhub` package. This introduces a supply chain risk as a malicious or breaking update to `clawhub` could compromise the agent's environment or functionality without explicit user consent or review. Pin the version of `clawhub` to a specific, known-good version (e.g., `npx clawhub@1.2.3 install project-agora`) to ensure deterministic and secure installations. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/a409882190a72bcc)
Powered by SkillShield