mcpbeat Sign in

Agent Bom Analyze Agent Skill

>- Analyze blast radius, attack paths, and threat landscape across your AI "attack path", "lateral movement", "context graph", "who can reach what".

1.1k tokens
context cost
SKILL.md, read when the skill is used
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
2 168
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/LeoYeAI/agent-master-skills --skill agent-bom-analyze

The instruction itself

7 sections, as written by the author

agent-bom-analyze — Blast Radius & Attack Path Analysis

Analyzes blast radius, attack paths, and the threat landscape across your AI

infrastructure. Maps lateral movement risks, identifies high-impact CVEs, and

visualizes agent context graphs.

Install

pipx install agent-bom
agent-bom agents --verbose   # blast radius detail for each agent
agent-bom graph              # generate context graph

When to Use

  • "blast radius" / "what's the blast radius"
  • "threat intel" / "threat intelligence"
  • "risk score" / "risk scoring"
  • "attack path" / "attack paths"
  • "lateral movement"
  • "context graph" / "agent graph"
  • "who can reach what"

Commands

# Blast radius detail (verbose)
agent-bom agents --verbose

# Generate context graph
agent-bom graph

Tools

| Tool | Description |

|------|-------------|

| blast_radius | Map CVE impact chain across agents, servers, and credentials |

| context_graph | Agent context graph with lateral movement analysis |

| analytics_query | Query vulnerability trends, posture history, and risk scores |

Examples

# Map blast radius of a specific CVE
blast_radius(cve_id="CVE-2024-21538")

# Build full context graph
context_graph()

# Query top CVEs by blast radius impact
analytics_query(query="top_blast_radius", days=30)

Example blast radius output:

CVE-2024-21538 — CRITICAL (CVSS 9.8, EPSS 0.94)
Blast Radius: 4 agents affected

  filesystem   [direct]  langchain 0.1.0 → CVE-2024-21538
    └─ github  [indirect] shares filesystem credential scope
    └─ slack   [indirect] accessible via filesystem tool call
  postgres     [direct]  langchain 0.1.0 → CVE-2024-21538

Recommended: Update langchain to ≥ 0.1.17

Guardrails

  • Analysis is read-only — no files are modified.
  • Only public CVE IDs are sent externally (to EPSS and vulnerability databases).
  • No internal config data, credentials, or agent details leave the machine.
  • Present blast radius findings clearly and ask the user whether to generate a remediation plan when CRITICAL CVEs are found.

How to use it

Copy the folder

Take leoyeai/agent-bom-analyze from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.