agent-bom scan

• Outcome: Review
• Latest audit: Aug 3, 2026 · 6:24 AM UTC
• Version: 0.98.3

Overview

This is a coherent security-scanning skill, but it can read many local AI-agent configuration files and its activation language is broad enough to deserve user review before installation.

Review before installing if you have private agent, MCP, Snowflake, or AI-tool configuration on this machine. Use it only for explicit security scans, prefer targeted package/image/SBOM checks when possible, and confirm what local config paths will be read before running full discovery.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The trigger phrases include broad language such as 'verify', 'is this safe', and 'scan dependencies', which can match ordinary user requests outside a narrowly scoped security-scanning context. In an agent environment, overly broad invocation criteria can cause the skill to activate unexpectedly and read local configuration or perform external lookups when the user did not intend this specific tool to run.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The 'When to Use' section repeats ambiguous phrases like 'verify' and 'is this safe' without guardrails tying them to packages, images, SBOMs, or CVE analysis. Because this skill has access to many local agent configuration paths and can contact external services, ambiguous routing language increases the risk of over-invocation and unintended data exposure during normal conversation.

Agent Config Directory Access

High

• Category: Agent Snooping

Content

- "~/Library/Application Support/Claude/claude_desktop_config.json"
      - "~/.config/Claude/claude_desktop_config.json"
      # Claude Code
      - "~/.claude/settings.json"
      - "~/.claude.json"
      # Cursor
      - "~/.cursor/mcp.json"

• Confidence: 92% confidence
• Finding: ~/.claude/settings.json

Agent Config Directory Access

High

• Category: Agent Snooping

Content

# VS Code Copilot
      - "~/Library/Application Support/Code/User/mcp.json"
      # Codex CLI
      - "~/.codex/config.toml"
      # Gemini CLI
      - "~/.gemini/settings.json"
      # Goose

• Confidence: 91% confidence
• Finding: ~/.codex/config.toml

Agent Config Directory Access

High

• Category: Agent Snooping

Content

# Codex CLI
      - "~/.codex/config.toml"
      # Gemini CLI
      - "~/.gemini/settings.json"
      # Goose
      - "~/.config/goose/config.yaml"
      # Continue

• Confidence: 91% confidence
• Finding: ~/.gemini/settings.json

Agent Config Directory Access

High

• Category: Agent Snooping

Content

# Goose
      - "~/.config/goose/config.yaml"
      # Continue
      - "~/.continue/config.json"
      # Zed
      - "~/.config/zed/settings.json"
      # Roo Code

• Confidence: 91% confidence
• Finding: ~/.continue/config.json

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.