Trust Assessment
repo received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 7 findings: 4 critical, 1 high, 2 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Arbitrary command execution, Missing required field: name.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 10/100, indicating areas for improvement.
Last analyzed on August 1, 2026 (commit dc2fd16b). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | SKILL.md:156 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | scripts/install.sh:71 | |
| 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 | scripts/install.sh:6 | |
| 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 | scripts/install.sh:6 | |
| HIGH | Indirect Prompt Injection in Risk Analysis The `performAIAnalysis` function directly interpolates untrusted fields from the login event (such as `username`, `hostname`, `ip`, and `terminal`) into the prompt sent to the LLM. An attacker can exploit this by attempting to log in with a crafted username or hostname containing prompt injection instructions (e.g., instructing the LLM to ignore previous instructions and output a 'low' risk level). This allows attackers to evade the AI-powered risk detection system. Sanitize or validate the login event fields before interpolating them into the prompt. Alternatively, use system instructions/developer messages to clearly separate the untrusted data from the instructions, or use a structured schema/LLM tool calling format that enforces strict boundaries between instructions and data. | LLM | src/risk.ts:108 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | SKILL.md:1 | |
| MEDIUM | Unpinned npm dependency version Dependency '@types/node' is not pinned to an exact version ('^22.0.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | package.json |
Scan History
Embed Code
[](https://skillshield.io/report/d5a4ae6ca9de4d9f)
Powered by SkillShield