Back to skill

Security audit

Maven Smart System Ai (palantir integration)

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent but high-impact: it connects to a military targeting system, stores an API key locally, and can change strike workflow state.

Install only if you are authorized to operate the referenced MSS environment and can verify the publisher and endpoint. Use least-privileged credentials, prefer read-only access unless mutation is required, protect or delete the .env file after use, and require an external human approval process before any target status change or asset assignment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill declares no permissions while clearly requiring environment access, local file read/write, and network-connected scripts. This under-declaration hides the true execution surface from reviewers and users, weakening consent and sandboxing decisions and making risky behaviors easier to slip through unnoticed.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the user to provide an MSS API key and then saves it to a local .env file without warning about persistence, file permissions, host exposure, or multi-user risk. Storing sensitive credentials locally can lead to accidental disclosure through backups, logs, repository commits, or other local processes reading the file.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script persists an API key to a project-level .env file in plaintext without any warning, consent prompt, or permission hardening. This creates a real risk of credential exposure through local compromise, accidental inclusion in source control, backups, logs, or broader filesystem access by other users/processes.

Credential Access

High
Category
Privilege Escalation
Content
tools:
  - name: initialize_config
    description: Saves the Palantir MSS API key and endpoint to the local .env file during initial setup.
    command: "python3 ./scripts/setup_env.py --key {{api_key}} --endpoint {{endpoint}}"
    parameters:
      api_key: string
Confidence
93% confidence
Finding
.env

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
python-dotenv>=1.0.0
Confidence
92% confidence
Finding
requests>=2.28.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
python-dotenv>=1.0.0
Confidence
90% confidence
Finding
python-dotenv>=1.0.0

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
97% confidence
Finding
requests

Known Vulnerable Dependency: python-dotenv — 1 advisory(ies): CVE-2026-28684 (python-dotenv: Symlink following in set_key allows arbitrary file overwrite via )

Low
Category
Supply Chain
Confidence
76% confidence
Finding
python-dotenv

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.