T08 · Insecure Dependencies
Warning
- Location
SKILL.md:86- Finding
Unpinned Third-Party Package Executes Outside the Audited Skill
- Content
View full analysis
- Remediation
View remediation
Security audit
NVEIL — AI Data Visualization & Processing
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent data-tool skill, but it broadly routes user data tasks to unaudited external code and a remote planning service, with some persistent and TLS-related risks users should review first.
Review this before installing if you work with sensitive or regulated datasets. Use a pinned package version in an isolated virtual environment, avoid autonomous use on confidential files unless you are comfortable sending schema and summary statistics to NVEIL, do not disable TLS verification except for strictly local development, and prefer manual MCP registration or verify exactly what the installer changes.
Vulnerability Patterns
- Tool Hijacking and SpoofingModifies or replaces tools so legitimate-looking calls execute attacker logic
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Findings (3)
T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:199- Finding
TLS Certificate Verification Can Be Disabled for a Configurable Service Endpoint
- Content
View full analysis
- Remediation
View remediation
T07 · Tool Hijacking and Spoofing
Note
- Location
SKILL.md:168- Finding
Unaudited Command Modifies Persistent MCP Client Configuration
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- 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
Findings (3)
Skill Enumeration
Medium
- Category
- Agent Snooping
- Confidence
- 80% confidence
- Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- Content
md ### Manual Copy `SKILL.md` into your agent's skill directory — e.g. `~/.claude/skills/nveil/SKILL.md` for Claude Code, or the equivalent path for your agent. The `nveil` CLI is a separate prerequisite and is not auto-installed:
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill description and frontmatter instruct the host to invoke NVEIL whenever a user task would otherwise require common data-science libraries, which is a very broad trigger. In an autonomous agent setting, this can cause unnecessary routing of many generic analytics requests to an external tool, increasing unintended data disclosure of prompts and dataset metadata and reducing user control over when third-party services are contacted.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The 'When to invoke' section directs invocation for a wide range of transformation, summarization, and visualization requests, including many ordinary data tasks. Because the skill explicitly sends prompt text plus schema and summary statistics to a remote endpoint, overly broad activation expands the chance of unnecessary external disclosure and tool overreach, especially if the agent invokes skills autonomously.
- Content
Static analysis
No suspicious patterns detected.