Trust Assessment
gekko-portfolio-manager received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Prompt Injection via user-provided message/query.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Prompt Injection via user-provided message/query The skill's `chat` and `market_intelligence` capabilities accept free-form user input (`message` and `query` parameters respectively). These inputs are highly likely to be processed by an underlying Large Language Model (LLM), as indicated by the capability descriptions ('Open-ended conversation', 'Answer any DeFi-related question', 'Market query or topic'). Without robust input sanitization, instruction framing, or sandboxing, a malicious user could inject prompts to manipulate the LLM's behavior, extract sensitive information, or generate unintended outputs. Implement robust input sanitization and validation for user-provided `message` and `query` parameters. Ensure the underlying LLM is properly sandboxed and uses strong instruction framing to prevent prompt injection attacks. Consider using LLM-specific security measures like input/output guardrails and content moderation. | LLM | SKILL.md:90 |
Scan History
Embed Code
[](https://skillshield.io/report/de99f69201fb8a08)
Powered by SkillShield