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, 7 high, 7 medium, and 1 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 12, 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-vault/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-vault/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-vault/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-vault/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-vault/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-vault/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-vault/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-vault/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-vault/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-vault/tests/test_smoke_cli.py:6 | |
| HIGH | Arbitrary File Content Exfiltration via Artifacts and Export The skill allows an agent to add an artifact by specifying an arbitrary file path on the host system via the `vault artifact add` CLI command or the `vault_add_artifact` MCP tool. The content of this file is then read by `scripts/synthesis.py:_read_text_file`, stored in the skill's SQLite database, and can subsequently be exported as part of the project data to another user-specified file path via `vault export --output`. This enables an attacker to read the content of any file accessible by the skill's process and exfiltrate it. Restrict artifact paths to a designated, sandboxed directory. Implement strict validation on file paths to prevent directory traversal (`../`) and access to sensitive system locations. For export, ensure the output directory is also restricted or that the content is sanitized if it contains sensitive data. | LLM | scripts/vault.py:109 | |
| 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-vault/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-vault/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-vault/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-vault/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-vault/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-vault/pyproject.toml | |
| MEDIUM | Stored Prompt Injection in Findings/Insights The skill allows agents to add findings/insights with arbitrary `title` and `content` strings via the `vault insight --add` CLI command and the `vault_add_finding` MCP tool. This user-controlled text is stored in the database and can be retrieved later. If this stored content is subsequently fed into an LLM (e.g., for summarization, synthesis, or further analysis) without proper sanitization, it could lead to prompt injection, manipulating the LLM's behavior. Implement strict input validation and sanitization for `title` and `content` fields, especially if they are intended for LLM consumption. When displaying or processing this content with an LLM, use techniques like XML tagging or specific delimiters to clearly separate user-provided data from system instructions. | LLM | scripts/vault.py:86 | |
| LOW | Arbitrary File Overwrite via Export Functionality The `vault export --output <file>` command allows writing the project's research data to any specified file path on the host system. While the content written is structured research data (JSON or Markdown), this capability could be misused to overwrite critical system files, potentially leading to denial of service or system instability. Restrict the output directory for exports to a designated, sandboxed location. Implement checks to prevent overwriting critical system files or writing outside the intended directory. | LLM | scripts/vault.py:46 |
Scan History
Embed Code
[](https://skillshield.io/report/12978124316e3ba1)
Powered by SkillShield