Trust Assessment
researchvault 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 25 findings: 6 critical, 10 high, 8 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Unsafe environment variable passthrough, Arbitrary command execution.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, 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 Findings25
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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/lraivisto/researchvault/tests/test_smoke_cli.py:7 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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/lraivisto/researchvault/tests/test_smoke_cli.py:150 | |
| CRITICAL | Credential harvesting Bulk environment variable dump Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/lraivisto/researchvault/tests/test_mcp_server.py:12 | |
| CRITICAL | Credential harvesting Bulk environment variable dump Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/lraivisto/researchvault/tests/test_smoke_cli.py:19 | |
| CRITICAL | Credential harvesting Bulk environment variable dump Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/lraivisto/researchvault/tests/test_smoke_cli.py:61 | |
| CRITICAL | Credential harvesting Bulk environment variable dump Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/lraivisto/researchvault/tests/test_smoke_cli.py:125 | |
| HIGH | 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/lraivisto/researchvault/tests/exploit_ssrf.py:10 | |
| HIGH | Unsafe environment variable passthrough Bulk environment variable harvesting Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/lraivisto/researchvault/tests/test_mcp_server.py:12 | |
| HIGH | Unsafe environment variable passthrough Bulk environment variable harvesting Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/lraivisto/researchvault/tests/test_smoke_cli.py:19 | |
| HIGH | Unsafe environment variable passthrough Bulk environment variable harvesting Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/lraivisto/researchvault/tests/test_smoke_cli.py:61 | |
| HIGH | Unsafe environment variable passthrough Bulk environment variable harvesting Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/lraivisto/researchvault/tests/test_smoke_cli.py:125 | |
| HIGH | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/lraivisto/researchvault/tests/conftest.py:46 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS resolution call that could be used for data exfiltration Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/lraivisto/researchvault/scripts/scuttle.py:64 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function '_run_cli'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/lraivisto/researchvault/tests/test_smoke_cli.py:7 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'test_smoke_strategy_json'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/lraivisto/researchvault/tests/test_smoke_cli.py:150 | |
| HIGH | Prompt Injection via user_query in LLM call The `plan_verification_missions` function in `scripts/core.py` constructs an LLM prompt that directly embeds the `user_query` parameter. An attacker could inject malicious instructions into this `user_query` to manipulate the LLM's behavior, potentially leading to unintended actions, data exposure, or denial of service. The `user_query` originates from user input via the `vault verify plan --query` command. Sanitize or strictly validate `user_query` before embedding it directly into the LLM prompt. Consider using a dedicated tool input for specific parameters rather than free-form text, or implement a robust input sanitization/validation layer to filter out prompt injection attempts. Alternatively, ensure the LLM is sandboxed and cannot perform sensitive actions based on user-provided prompts. | LLM | scripts/core.py:570 | |
| MEDIUM | 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/lraivisto/researchvault/tests/exploit_ssrf.py:8 | |
| MEDIUM | 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/lraivisto/researchvault/tests/exploit_ssrf.py:21 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/lraivisto/researchvault/scripts/core.py:7 | |
| MEDIUM | Suspicious import: socket Import of 'socket' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/lraivisto/researchvault/scripts/scuttle.py:5 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/lraivisto/researchvault/scripts/scuttle.py:7 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/lraivisto/researchvault/tests/test_grokipedia.py:2 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/lraivisto/researchvault/tests/test_youtube.py:2 | |
| MEDIUM | Unpinned Python dependency version Dependency 'requests>=2.32.0' is not pinned to an exact version. Pin Python dependencies with exact versions where feasible. | Dependencies | skills/lraivisto/researchvault/pyproject.toml | |
| LOW | Unpinned or Loosely Pinned Dependencies The `pyproject.toml` file specifies dependencies using the `>=` operator (e.g., `requests>=2.32.0`). While this allows for minor updates, it does not pin dependencies to exact versions. This practice can introduce supply chain risks if a future version of a dependency contains a vulnerability or breaking change, as it could be automatically installed without explicit review. This is a common practice but less secure than exact pinning. Pin all dependencies to exact versions (e.g., `requests==2.32.0`) to ensure deterministic builds and prevent unexpected vulnerabilities or breaking changes from being introduced by new dependency versions. Use a dependency management tool (like `pip-compile` from `pip-tools`) to manage and update pinned dependencies explicitly. | LLM | pyproject.toml:12 |
Scan History
Embed Code
[](https://skillshield.io/report/bfbe37acd1a9a35d)
Powered by SkillShield