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: 5 critical, 6 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 13, 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/lraivisto-researchvault/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/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/lraivisto-researchvault/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/lraivisto-researchvault/tests/test_smoke_cli.py:60 | |
| CRITICAL | Arbitrary File Read via `vault_add_artifact` The `vault_add_artifact` tool exposed via the MCP server allows an agent to specify an arbitrary `path` to a local file. This path is then read by the `_read_text_file` function in `scripts/synthesis.py` and its content is processed. This constitutes a critical data exfiltration vulnerability, as a malicious agent could instruct the skill to read sensitive files from its execution environment (e.g., `/etc/passwd`, API keys, configuration files) and potentially exfiltrate their contents. Restrict the `path` argument in `vault_add_artifact` to a predefined, sandboxed directory (e.g., a `data/` subdirectory within the skill's workspace). Implement strict validation to ensure the path does not escape this directory (e.g., by disallowing `..` or absolute paths). Alternatively, remove the ability to specify arbitrary local file paths and instead require content to be passed directly or fetched from trusted sources. | LLM | scripts/mcp_server.py:139 | |
| 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/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/lraivisto-researchvault/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/lraivisto-researchvault/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/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/lraivisto-researchvault/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/lraivisto-researchvault/tests/test_smoke_cli.py:6 | |
| 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/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/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/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/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/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/lraivisto-researchvault/pyproject.toml | |
| MEDIUM | Potential Server-Side Request Forgery (SSRF) via URL Ingestion The `scripts/scuttle.py` module, used for ingesting content from URLs, implements hostname and IP blocking (`_is_blocked_host`, `_is_blocked_ip`) to prevent SSRF. However, the `requests.get` calls do not explicitly disable redirects. A sophisticated attacker could potentially bypass these checks by providing a URL to an external server that then redirects to an internal IP address or sensitive endpoint, leading to an SSRF vulnerability. This could allow the skill to make requests to internal network resources that should not be publicly accessible. Explicitly disable redirects for all `requests.get` calls that handle user-provided URLs by adding `allow_redirects=False`. If redirects are necessary, re-evaluate the redirected URL against the same `_ensure_safe_url` checks before making the request. | LLM | scripts/scuttle.py:130 | |
| LOW | Unpinned Dependencies in `pyproject.toml` The `pyproject.toml` file specifies dependencies using `>=` (e.g., `requests>=2.32.0`). While `uv` is used for installation, which typically generates a lockfile, relying solely on `>=` in the manifest can lead to non-deterministic builds if the lockfile is not strictly enforced or if `uv` is not always used. This increases the risk of unexpected dependency updates introducing breaking changes, vulnerabilities, or even malicious code if a package maintainer pushes a compromised version within the allowed range. Pin all production dependencies to exact versions using `==` (e.g., `requests==2.32.0`). This ensures reproducible builds and prevents unexpected changes from upstream dependencies. If `uv` is intended to manage exact versions, ensure that a `uv.lock` file is committed and that the installation process strictly uses it. | LLM | pyproject.toml:12 |
Scan History
Embed Code
[](https://skillshield.io/report/9261c2187af1f3a3)
Powered by SkillShield