Trust Assessment
openviking 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 6 findings: 4 critical, 1 high, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Arbitrary command execution, Remote code execution: curl/wget pipe to shell.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.
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 Findings6
| 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 | skills/zaynjarvis/openviking/SKILL.md:56 | |
| 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 | skills/zaynjarvis/openviking/scripts/init.sh:13 | |
| 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 | skills/zaynjarvis/openviking/scripts/init.sh:13 | |
| CRITICAL | Malicious repository clone and dependency installation via environment variable The `scripts/init.sh` script clones the OpenViking repository and installs its dependencies using `uv sync`. The `REPO_URL` for `git clone` is derived from the `OPENVIKING_REPO` environment variable if set, otherwise it defaults to `https://github.com/volcengine/OpenViking.git`. An attacker could manipulate the agent's environment to set `OPENVIKING_REPO` to point to a malicious Git repository. This would cause the skill to clone attacker-controlled code and then install attacker-defined dependencies via `uv sync`, leading to arbitrary code execution within the agent's environment. Remove the ability to override `REPO_URL` via environment variables. Hardcode the trusted repository URL. Implement content hash verification for cloned repositories and their dependencies to ensure integrity. | LLM | scripts/init.sh:7 | |
| HIGH | Arbitrary local file read and potential exfiltration via `add_resource` tool The skill's `add_resource` tool is explicitly designed to "Add files, directories, or URLs" to the knowledge base, as described in `SKILL.md`. The example usage `Add ~/documents/report.pdf` confirms the ability to read arbitrary local files. If an attacker can prompt the agent to use `add_resource` with a path to a sensitive file (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, API keys), the skill will read this content and store it in its vector memory. Subsequent queries to the knowledge base could then be used to exfiltrate this sensitive data. This also represents excessive permissions as the tool has broad, unrestricted filesystem read access. Restrict the `add_resource` tool to specific, safe directories or file types. Implement strict input validation and sanitization for file paths and URLs. Explicitly block access to sensitive file paths or require user confirmation for such access. Implement data redaction or access controls for retrieved content to prevent exfiltration. | LLM | SKILL.md:67 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/zaynjarvis/openviking/scripts/init.sh:7 |
Scan History
Embed Code
[](https://skillshield.io/report/f2cea60f576a7a06)
Powered by SkillShield