agent-bom

An open security scanner for AI-agent setups, including agents, MCP servers, packages, skills, and their access to credentials and tools. MCP is a standard way for an AI agent to connect to external tools.

In plain words
What is it for?
Use it to scan agent infrastructure, check packages for CVEs, assess skills and MCP servers, map blast radius, create software bills of materials, or verify package provenance.
Why use it?
It helps identify known vulnerabilities, supply-chain risks, exposed credentials, unsafe configurations, and the possible reach of a security problem.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/msaad00/agent-bom/cortex-code
Any agent
npx skills add msaad00/agent-bom --skill cortex-code
Clone the repo
git clone --depth 1 https://github.com/msaad00/agent-bom

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 960 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00960
Opus 5 $0.00019 $0.00480
Sonnet 5 $0.00008 $0.00192
Haiku 4.5 $0.00004 $0.00096

Measured 2d ago against content hash e18b9a45a22c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-bom scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

integrations/cortex-code/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-bom — Security Platform for Agentic Infrastructure

Scan your MCP servers, AI agents, and their packages: CVEs and supply-chain risk (malicious/typosquat) in the packages, plus credential exposure, identity/auth/access posture, and MCP config risk on the servers and agents. Maps blast radius from a finding to the credentials and tools it can reach.

When to Use

  • Before installing a new MCP server or skill
  • To audit your Cortex Code MCP configuration for vulnerabilities
  • To check if a specific package has known CVEs
  • To map the blast radius of a vulnerability across your agent setup
  • To generate an SBOM for compliance (CycloneDX, SPDX)
  • To verify package integrity via Sigstore provenance

What This Skill Provides

  • CVE scanning with enrichment from OSV, NVD, EPSS, CISA KEV
  • MCP server discovery across real AI developer tools, including Cortex Code
  • Blast radius mapping — which agents, credentials, and tools are exposed
  • Compliance mapping across OWASP, NIST, MITRE, EU AI Act, and related frameworks
  • Runtime proxy for MCP traffic interception and policy enforcement
  • SKILL.md trust assessment with 17 behavioral risk patterns

Install

# Install via pip or pipx
pipx install agent-bom

# Or run directly with uvx (no install needed)
uvx agent-bom scan

Instructions

Scan the current MCP setup

agent-bom scan

Auto-discovers all configured MCP clients (Cortex Code, Claude Desktop, Cursor, etc.), resolves their server packages, and scans for CVEs.

Check a package before installing

agent-bom check <package>@<version> --ecosystem <npm|pypi|go|maven|cargo|nuget|gem>

Map blast radius of a CVE

agent-bom scan --enrich
# Then review the blast radius section in the output

Generate SBOM

agent-bom scan -f cyclonedx -o sbom.json
agent-bom scan -f spdx -o sbom.spdx.json

Scan with GPU infrastructure detection

agent-bom scan --gpu-scan

Read the full file on GitHub · 130 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 130 lines · 39 tokens per session scan A e18b9a45a22c

Subscribe to this mod's changes

agent-bom is a skill published in the GitHub repository msaad00/agent-bom (31 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 960 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

sbom-analysis

Analyzes Software Bills of Materials (SBOMs) for completeness against NTIA minimum elements, interprets VEX status documents, performs transitive dependency risk analysis, and detects license conflicts. Supports CycloneDX 1.5 and SPDX 2.3 formats with CSAF-based VEX correlation. Auto-invoked when SBOM files are…

UnitOneAI/SecuritySkills · 89 tokens

dependency-scanning

Analyzes project dependencies for known vulnerabilities, license risks, and supply chain integrity. Auto-invoked when package manifests (package.json, requirements.txt, go.mod, pom.xml, Cargo.toml) are shared or when discussing dependency security. Produces an SBOM assessment with CVE findings triaged by EPSS and CISA…

UnitOneAI/SecuritySkills · 83 tokens

sca-trivy

Software Composition Analysis (SCA) and container vulnerability scanning using Aqua Trivy for identifying CVE vulnerabilities in dependencies, container images, IaC misconfigurations, and license compliance risks. Use when: (1) Scanning container images and filesystems for vulnerabilities and misconfigurations, (2)…

AgentSecOps/SecOpsAgentKit · 156 tokens

container-grype

Container vulnerability scanning and dependency risk assessment using Grype with CVSS severity ratings, EPSS exploit probability, and CISA KEV indicators. Use when: (1) Scanning container images and filesystems for known vulnerabilities, (2) Integrating vulnerability scanning into CI/CD pipelines with severity…

AgentSecOps/SecOpsAgentKit · 134 tokens

sca-trivy

Software Composition Analysis (SCA) and container vulnerability scanning using Aqua Trivy for identifying CVE vulnerabilities in dependencies, container images, IaC misconfigurations, and license compliance risks. Use when: (1) Scanning container images and filesystems for vulnerabilities and misconfigurations, (2)…

rohunj/claude-build-workflow · 156 tokens

bugcrowd-reporting

Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints…

elementalsouls/Claude-BugHunter · 171 tokens