Trust Assessment
render-deploy received a trust score of 27/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 2 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Untrusted Instruction for Sandbox Privilege Escalation.
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 October 1, 2026 (commit 120b6767). 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 | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | packages/skills-catalog/skills/(cloud)/render-deploy/SKILL.md:152 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | packages/skills-catalog/skills/(cloud)/render-deploy/SKILL.md:152 | |
| HIGH | Untrusted Instruction for Sandbox Privilege Escalation The skill document contains instructions directing the host LLM to bypass sandbox restrictions by rerunning commands with escalated permissions ('sandbox_permissions=require_escalated') or prompting the user to grant escalated network access. Since skill files are treated as untrusted input, these instructions could be exploited to manipulate the agent into escaping its sandbox or performing unauthorized network activities. Remove instructions that direct the LLM to escalate sandbox permissions or bypass security controls. The agent's security posture and sandbox boundaries should be managed solely by the host environment, not influenced by instructions within the skill package. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/190f51c94e06de70)
Powered by SkillShield