Agent Audit MCP Server
by HeadyZhangStatic security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.
Agent Audit is an open-source mcp server by HeadyZhang, written mainly in Python, with 245 GitHub stars and the MIT license. Its code was last updated Sep 13, 2026.
Scan summary: scanned Nov 5, 2026 at commit 8c4c5cb. No capabilities flagged by our checks. Scan policy
ScannedScanned. The automated checks below ran on the commit shown. Read each line for what was and was not covered.
Full scan at
8c4c5cb · Nov 5, 2026 ScannedStatic, secrets and dependency checks completed with no critical findings.
Passed. This check ran and found nothing it flags.Static code scanpassPassed. This check ran and found nothing it flags.
Flagged. This check found an issue. See the findings below.Secrets scanfailFlagged. This check found an issue. See the findings below.
Flagged. This check found an issue. See the findings below.Dependency audit101 known vulnerabilitiesfailFlagged. This check found an issue. See the findings below.
Warning. This check found something worth reading in the findings below. It is not proof of a problem.ManifestnonewarnWarning. This check found something worth reading in the findings below. It is not proof of a problem.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Buildn/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Boot & handshaken/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Network egressn/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Not applicable. This check does not apply to this kind of project, or it was not run in this scan.Reproducible (×3)n/aNot applicable. This check does not apply to this kind of project, or it was not run in this scan.
Findings (39)
- highHigh. Something risky that needs a close look before you install.secrets issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.secrets issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dependencies issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dependencies issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dependencies issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dependencies issueDetails are available to the maintainer after claiming this listing.
- highHigh. Something risky that needs a close look before you install.dependencies issueDetails are available to the maintainer after claiming this listing.
- lowLow. Minor, or common in normal tools. Shown for information.In tests/examples/docs: Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
examples/06-vulnerable-agent-demo/agent.py:21 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
examples/06-vulnerable-agent-demo/agent.py:9 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key2 matches in this file
docs/RULES.md:293 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/benchmark/agent-vuln-bench/datasets/wilds/WILD-007/vuln/mcp_config.json:33 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: slack-bot-token
tests/benchmark/agent-vuln-bench/datasets/wilds/WILD-004/vuln/token_collector.py:13 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key2 matches in this file
tests/benchmark/agent-vuln-bench/datasets/wilds/WILD-004/vuln/token_collector.py:9 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/benchmark/fixtures/mcp_config.json:32 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/fixtures/asi-03-privilege-abuse/direct/hardcoded_api_key.py:11 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: stripe-access-token
tests/test_analysis/test_value_analyzer.py:71 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: github-pat
tests/test_analysis/test_value_analyzer.py:62 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key5 matches in this file
tests/test_analysis/test_value_analyzer.py:32 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/fixtures/mcp_configs/vulnerable_config.json:15 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key2 matches in this file
tests/fixtures/vulnerable_agents/data_exfiltration.py:24 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/test_parsers/test_treesitter_parser.py:62 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/test_analysis/test_framework_detector.py:26 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/test_analysis/test_entropy.py:43 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/differential_corpus/py/secrets.py:28 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: jwt
tests/benchmark/agent-vuln-bench/datasets/knowns/KNOWN-009/vuln/jwt_hardcoded.py:6 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/test_rules/test_engine.py:140 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/fixtures/asi-05-rce/direct/credential_new_formats.py:5 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key2 matches in this file
tests/test_analysis/test_hex_digest_shape.py:115 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/test_scanners/test_mcp_config_scanner_ext.py:150 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: jwt2 matches in this file
tests/test_secret_scanner_payment.py:30 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/test_secret_scanner_payment.py:104 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key
tests/test_scanners/test_mcp_scanner_v030.py:222 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: aws-access-token
tests/test_agent004_semantic.py:257 - lowLow. Minor, or common in normal tools. Shown for information.Possible example credential in docs/tests: generic-api-key3 matches in this file
tests/test_analysis/test_uuid_detection.py:51 - lowLow. Minor, or common in normal tools. Shown for information.idna@3.11: 1 known vulnerabilityPYSEC-2026-215
packages/audit/poetry.lock - lowLow. Minor, or common in normal tools. Shown for information.multidict@6.7.1: 1 known vulnerabilityPYSEC-2026-4244
packages/audit/poetry.lock - lowLow. Minor, or common in normal tools. Shown for information.pygments@2.19.2: 1 known vulnerabilityPYSEC-2026-2987
packages/audit/poetry.lock - lowLow. Minor, or common in normal tools. Shown for information.pytest@7.4.4: 1 known vulnerabilityPYSEC-2026-1845
packages/audit/poetry.lock - lowLow. Minor, or common in normal tools. Shown for information.No manifest declaring network access and environment variables (agent.json)
Automated result for the commit shown. See our scan policy. View the scan log
Maintainers can claim the listing to rescan, or dispute a result.
Agent Audit alternatives
View more →Similar mcp servers in Security & Testing, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Agent Audit (this page) HeadyZhang | 245 | MIT | Sep 13, 2026 | Scanned, no flagged issues |
| Hexstrike AI 0x4m4 | 13k | MIT | Aug 3, 2026 | Scanned, no flagged issues |
| Viper FunnyWolf | 5.3k | None found | May 31, 2026 | Not scanned yet |
| Open Ontologies fabio-rovai | 2.7k | MIT | Oct 30, 2026 | Scanned, no flagged issues |
| Qu1cksc0pe CYB3RMX | 2.1k | GPL-3.0 | Sep 18, 2026 | Scanned, no flagged issues |
| Cve MCP Server mukul975 | 1.7k | Apache-2.0 | Oct 1, 2026 | Scanned, no flagged issues |