agent-bom-compliance — AI Compliance & Policy Engine
Evaluate AI infrastructure scan results against 14 security and regulatory
frameworks. Enforce policy-as-code rules. Generate SBOMs in standard formats.
Run AISVS v1.0 and CIS benchmark checks.
Install
pipx install agent-bom
agent-bom agents -f compliance-export # run agents scan with compliance export
agent-bom generate-sbom # generate CycloneDX SBOM
When to Use
- "compliance report" / "run compliance"
- "NIST" / "NIST AI RMF" / "NIST CSF" / "NIST 800-53"
- "SOC 2" / "SOC2"
- "ISO 27001"
- "OWASP" / "OWASP LLM Top 10" / "OWASP Agentic Top 10"
- "EU AI Act"
- "AISVS" / "AI Security Verification Standard"
- "CMMC" / "FedRAMP"
- "generate SBOM" / "CycloneDX" / "SPDX"
- "policy check" / "policy enforcement"
Tools (5)
| Tool |
Description |
compliance |
OWASP LLM/Agentic Top 10, EU AI Act, MITRE ATLAS, NIST AI RMF |
policy_check |
Evaluate results against custom security policy (17 conditions) |
cis_benchmark |
Run CIS benchmark checks against cloud accounts |
generate_sbom |
Generate SBOM (CycloneDX or SPDX format) |
aisvs_benchmark |
OWASP AISVS v1.0 compliance — 9 AI security checks |
Supported Frameworks (14)
- OWASP LLM Top 10 (2025) — prompt injection, supply chain, data leakage
- OWASP MCP Top 10 — MCP-specific security risks
- OWASP Agentic Top 10 — tool poisoning, rug pulls, credential theft
- OWASP AISVS v1.0 — AI Security Verification Standard (9 checks)
- MITRE ATLAS — adversarial ML threat framework
- NIST AI RMF — govern, map, measure, manage lifecycle
- NIST CSF 2.0 — identify, protect, detect, respond, recover
- NIST 800-53 Rev 5 — federal security controls (CM-8, RA-5, SI-2, SR-3)
- FedRAMP Moderate — derived from NIST 800-53 controls
- EU AI Act — risk classification, transparency, SBOM requirements
- ISO 27001:2022 — information security controls (Annex A)
- SOC 2 — Trust Services Criteria
- CIS Controls v8 — implementation groups IG1/IG2/IG3
- CMMC 2.0 — cybersecurity maturity model (Level 1-3)
Examples
# Run compliance check against multiple frameworks
compliance(frameworks=["owasp_llm", "eu_ai_act", "nist_ai_rmf"])
# Enforce custom policy
policy_check(policy={"max_critical": 0, "max_high": 5})
# Generate SBOM
generate_sbom(format="cyclonedx")
# Run AISVS v1.0 compliance
aisvs_benchmark()
# Run AWS CIS benchmark
cis_benchmark(provider="aws")
Privacy & Data Handling
OWASP, NIST, EU AI Act, MITRE ATLAS, AISVS, SBOM generation, and policy
checks run entirely locally on scan data already in memory. No network calls,
no credentials needed for these features.
CIS benchmark checks (optional, user-initiated) call cloud provider APIs
using your locally configured credentials. These are read-only API calls to
AWS, Azure, GCP, or Snowflake. You must explicitly run cis_benchmark(provider=...)
and confirm before any cloud API calls are made.
Verification
1---2name: agent-bom-compliance3description: >-4 AI compliance and policy engine — evaluate scan results against OWASP, NIST,5 SOC 2, ISO 27001, CMMC, EU AI Act, AISVS v1.0, and related frameworks.6 Generate SBOMs and compliance reports. Use when:7 "compliance report", "NIST", "SOC 2", "ISO 27001", "OWASP", "EU AI Act",8 "AISVS", "generate SBOM", "policy check".9version: 0.75.1010license: Apache-2.011compatibility: >-12 Requires Python 3.11+. Install via pipx or pip. OWASP/NIST/EU AI Act/MITRE13 evaluation and SBOM generation are fully local with zero credentials. CIS14 benchmark checks optionally use cloud SDK credentials (AWS/Azure/GCP/Snowflake)15 and make read-only API calls to cloud providers when explicitly invoked.16metadata:17 author: msaad0018 homepage: https://github.com/msaad00/agent-bom19 source: https://skillmd.com/skills/leoyeai-openclaw-master-skills/agent-bom-compliance20 upstream: https://github.com/msaad00/agent-bom21 pypi: https://pypi.org/project/agent-bom/22 scorecard: https://securityscorecards.dev/viewer/?uri=github.com/msaad00/agent-bom23 tests: 653324 install:25 pipx: agent-bom26 pip: agent-bom27 docker: ghcr.io/msaad00/agent-bom:0.75.1028 openclaw:29 requires:30 bins: []31 env: []32 credentials: none33 credential_policy: "Zero credentials required for OWASP/NIST/EU AI Act compliance and SBOM generation. CIS benchmark checks (AWS, Azure, GCP, Snowflake) optionally accept cloud credentials — only used locally to call cloud APIs, never transmitted elsewhere."34 optional_env:35 - name: AWS_PROFILE36 purpose: "AWS CIS benchmark checks — uses boto3 with your local AWS profile"37 required: false38 - name: AZURE_TENANT_ID39 purpose: "Azure CIS benchmark checks (azure-mgmt-* SDK)"40 required: false41 - name: AZURE_CLIENT_ID42 purpose: "Azure CIS benchmark checks — service principal client ID"43 required: false44 - name: AZURE_CLIENT_SECRET45 purpose: "Azure CIS benchmark checks — service principal secret"46 required: false47 - name: GOOGLE_APPLICATION_CREDENTIALS48 purpose: "GCP CIS benchmark checks (google-cloud-* SDK)"49 required: false50 - name: SNOWFLAKE_ACCOUNT51 purpose: "Snowflake CIS benchmark checks"52 required: false53 - name: SNOWFLAKE_USER54 purpose: "Snowflake CIS benchmark checks"55 required: false56 - name: SNOWFLAKE_PRIVATE_KEY_PATH57 purpose: "Snowflake key-pair auth (CI/CD)"58 required: false59 - name: SNOWFLAKE_AUTHENTICATOR60 purpose: "Snowflake auth method (default: externalbrowser SSO)"61 required: false62 optional_bins: []63 emoji: "\U00002705"64 homepage: https://github.com/msaad00/agent-bom65 source: https://github.com/msaad00/agent-bom66 license: Apache-2.067 os:68 - darwin69 - linux70 - windows71 data_flow: >-72 OWASP/NIST/EU AI Act/MITRE/SBOM evaluation is purely local — zero network73 calls. CIS benchmark checks (optional, user-initiated) call cloud provider74 APIs (AWS/Azure/GCP/Snowflake) using locally configured credentials. No data75 is stored or transmitted beyond the cloud provider's own API. File reads are76 limited to user-provided SBOMs and policy files.77 file_reads:78 - "user-provided SBOM files (CycloneDX/SPDX JSON)"79 - "user-provided policy files (YAML/JSON policy-as-code)"80 file_writes: []81 network_endpoints:82 - url: "https://*.amazonaws.com"83 purpose: "AWS CIS benchmark checks — read-only API calls (IAM, S3, CloudTrail, etc.)"84 auth: true85 optional: true86 - url: "https://management.azure.com"87 purpose: "Azure CIS benchmark checks — read-only API calls (Azure Resource Manager)"88 auth: true89 optional: true90 - url: "https://*.googleapis.com"91 purpose: "GCP CIS benchmark checks — read-only API calls (Cloud Resource Manager, IAM, etc.)"92 auth: true93 optional: true94 - url: "https://*.snowflakecomputing.com"95 purpose: "Snowflake CIS benchmark checks — read-only API calls (ACCOUNT_USAGE views)"96 auth: true97 optional: true98 telemetry: false99 persistence: false100 privilege_escalation: false101 always: false102 autonomous_invocation: restricted103---104105# agent-bom-compliance — AI Compliance & Policy Engine106107Evaluate AI infrastructure scan results against 14 security and regulatory108frameworks. Enforce policy-as-code rules. Generate SBOMs in standard formats.109Run AISVS v1.0 and CIS benchmark checks.110111## Install112113```bash114pipx install agent-bom115agent-bom agents -f compliance-export # run agents scan with compliance export116agent-bom generate-sbom # generate CycloneDX SBOM117```118119## When to Use120121- "compliance report" / "run compliance"122- "NIST" / "NIST AI RMF" / "NIST CSF" / "NIST 800-53"123- "SOC 2" / "SOC2"124- "ISO 27001"125- "OWASP" / "OWASP LLM Top 10" / "OWASP Agentic Top 10"126- "EU AI Act"127- "AISVS" / "AI Security Verification Standard"128- "CMMC" / "FedRAMP"129- "generate SBOM" / "CycloneDX" / "SPDX"130- "policy check" / "policy enforcement"131132## Tools (5)133134| Tool | Description |135|------|-------------|136| `compliance` | OWASP LLM/Agentic Top 10, EU AI Act, MITRE ATLAS, NIST AI RMF |137| `policy_check` | Evaluate results against custom security policy (17 conditions) |138| `cis_benchmark` | Run CIS benchmark checks against cloud accounts |139| `generate_sbom` | Generate SBOM (CycloneDX or SPDX format) |140| `aisvs_benchmark` | OWASP AISVS v1.0 compliance — 9 AI security checks |141142## Supported Frameworks (14)143144- **OWASP LLM Top 10** (2025) — prompt injection, supply chain, data leakage145- **OWASP MCP Top 10** — MCP-specific security risks146- **OWASP Agentic Top 10** — tool poisoning, rug pulls, credential theft147- **OWASP AISVS v1.0** — AI Security Verification Standard (9 checks)148- **MITRE ATLAS** — adversarial ML threat framework149- **NIST AI RMF** — govern, map, measure, manage lifecycle150- **NIST CSF 2.0** — identify, protect, detect, respond, recover151- **NIST 800-53 Rev 5** — federal security controls (CM-8, RA-5, SI-2, SR-3)152- **FedRAMP Moderate** — derived from NIST 800-53 controls153- **EU AI Act** — risk classification, transparency, SBOM requirements154- **ISO 27001:2022** — information security controls (Annex A)155- **SOC 2** — Trust Services Criteria156- **CIS Controls v8** — implementation groups IG1/IG2/IG3157- **CMMC 2.0** — cybersecurity maturity model (Level 1-3)158159## Examples160161```162# Run compliance check against multiple frameworks163compliance(frameworks=["owasp_llm", "eu_ai_act", "nist_ai_rmf"])164165# Enforce custom policy166policy_check(policy={"max_critical": 0, "max_high": 5})167168# Generate SBOM169generate_sbom(format="cyclonedx")170171# Run AISVS v1.0 compliance172aisvs_benchmark()173174# Run AWS CIS benchmark175cis_benchmark(provider="aws")176```177178## Privacy & Data Handling179180**OWASP, NIST, EU AI Act, MITRE ATLAS, AISVS, SBOM generation, and policy181checks** run entirely locally on scan data already in memory. No network calls,182no credentials needed for these features.183184**CIS benchmark checks** (optional, user-initiated) call cloud provider APIs185using your locally configured credentials. These are read-only API calls to186AWS, Azure, GCP, or Snowflake. You must explicitly run `cis_benchmark(provider=...)`187and confirm before any cloud API calls are made.188189## Verification190191- **Source**: [github.com/msaad00/agent-bom](https://github.com/msaad00/agent-bom) (Apache-2.0)192- **6,533+ tests** with CodeQL + OpenSSF Scorecard193- **No telemetry**: Zero tracking, zero analytics