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 19 findings: 4 critical, 8 high, 7 medium, and 0 low severity. Key findings include Unsafe environment variable passthrough, Arbitrary command execution, Credential harvesting.
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 Findings19
| 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/luka-rv-brain/tests/test_smoke_cli.py:6 | |
| 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/luka-rv-brain/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/luka-rv-brain/tests/test_smoke_cli.py:18 | |
| 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/luka-rv-brain/tests/test_smoke_cli.py:60 | |
| 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/luka-rv-brain/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/luka-rv-brain/tests/test_smoke_cli.py:18 | |
| 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/luka-rv-brain/tests/test_smoke_cli.py:60 | |
| 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/luka-rv-brain/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/luka-rv-brain/scripts/scuttle.py:35 | |
| 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/luka-rv-brain/tests/test_smoke_cli.py:6 | |
| HIGH | Arbitrary Local File Read via Artifacts The `vault_add_artifact` tool, exposed via the MCP server and CLI, allows an AI agent to specify an arbitrary local file path. The `synthesize` function then reads the content of this file into memory to generate embeddings. While the raw file content is not directly output, the LLM processing this content could be prompted to infer or describe sensitive information from these files, leading to data exfiltration. An attacker could instruct the agent to add an artifact pointing to sensitive system files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`). Implement strict validation and sandboxing for artifact paths. Only allow paths within a designated, non-sensitive data directory (e.g., a sub-directory of the skill's workspace). Consider whitelisting file extensions or types. If reading arbitrary files is strictly necessary, ensure the content is never exposed or processed in a way that could leak information to the LLM or external systems. | LLM | scripts/mcp_server.py:159 | |
| HIGH | Server-Side Request Forgery (SSRF) via Weak URL Validation in YouTube Connector The `YouTubeConnector`'s `can_handle` method uses a weak string-based check (`"youtube.com" in url or "youtu.be" in url`) to determine if it can process a URL. Its `fetch` method then directly makes an HTTP request to the user-provided URL using `requests.get` without applying the robust `_ensure_safe_url` checks present in other connectors. An attacker could craft a URL like `https://youtube.com.evil.com` or `https://internal-host/youtube.com` to bypass the `can_handle` check and then perform Server-Side Request Forgery (SSRF) against internal network resources or other external services. Apply the `_ensure_safe_url` function to the `url` parameter within the `YouTubeConnector.fetch` method before making the `requests.get` call. Additionally, strengthen the `can_handle` method to use more robust URL parsing and hostname validation (e.g., `urlparse` and checking `netloc` for exact domain matches or proper subdomains) to prevent bypasses. | LLM | scripts/scuttle.py:209 | |
| 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/luka-rv-brain/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/luka-rv-brain/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/luka-rv-brain/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/luka-rv-brain/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/luka-rv-brain/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/luka-rv-brain/pyproject.toml | |
| MEDIUM | Excessive Permissions: Arbitrary Database Path via Environment Variable The `scripts/db.py` module allows the `RESEARCHVAULT_DB` environment variable to completely override the default SQLite database path. If an AI agent or an attacker can control this environment variable, they could direct the skill to create or modify database files in arbitrary system locations (e.g., `/tmp`, `/etc`, `/var/log`), potentially leading to denial of service (filling critical directories), data corruption, or interference with other applications. While SQLite itself doesn't execute arbitrary code from the DB file, the ability to write to arbitrary paths is an excessive permission. Restrict the `RESEARCHVAULT_DB` environment variable to paths within a designated, non-sensitive data directory (e.g., `~/.researchvault/` or a sub-directory of the skill's workspace). Validate the `env_path` to ensure it does not escape this allowed directory (e.g., by checking for `..` or absolute paths outside the allowed base). | LLM | scripts/db.py:8 |
Scan History
Embed Code
[](https://skillshield.io/report/e0fd83ea4803353b)
Powered by SkillShield