Add AgentCore Policy samples: tool access control and guardrails as policies

[BharathiSrini]

Summary

• Adds 01-tool-access-with-policy/: demonstrates using AgentCore Policy to control which tools an agent can invoke based on request attributes (approval workflows, risk scoring)
• Adds 03-guardrails-as-policies/: demonstrates using Amazon Bedrock Guardrails as a policy layer to filter agent inputs and outputs
• Both samples include deploy.py, cleanup.py, demo scripts, utils (agent + JS tools), requirements.txt, and a README

Files added

01-features/07-centralize-and-govern-your-ai-infrastructure/02-policy/
├── 01-tool-access-with-policy/
│   ├── README.md
│   ├── deploy.py / cleanup.py / policy_demo.py
│   ├── requirements.txt
│   └── utils/  (agent_with_tools.py, application_tool.js, approval_tool.js, risk_model_tool.js)
└── 03-guardrails-as-policies/
    ├── README.md
    ├── deploy.py / cleanup.py / guardrail_demo.py
    ├── requirements.txt
    └── utils/  (agent_with_tools.py, application_tool.js, approval_tool.js, risk_model_tool.js)

Test plan

• Deploy tool-access-with-policy sample (python deploy.py) and verify agent runtime reaches READY state
• Run policy_demo.py and confirm tool access is correctly allowed/blocked per policy rules
• Deploy guardrails-as-policies sample and verify guardrail filtering on agent inputs/outputs
• Run cleanup.py for both samples to confirm teardown completes without errors

[github-actions]

Latest scan for commit: 4f704e9 | Updated: 2026-06-22 20:34:03 UTC

Security Scan Results

Scan Metadata

• Project: ASH
• Scan executed: 2026-06-22T20:33:45+00:00
• ASH version: 3.0.0

Summary

Scanner Results

The table below shows findings by scanner, with status based on severity thresholds and dependencies:

Column Explanations:

Severity Levels (S/C/H/M/L/I):

• Suppressed (S): Security findings that have been explicitly suppressed/ignored and don't affect the scanner's pass/fail status
• Critical (C): The most severe security vulnerabilities requiring immediate remediation (e.g., SQL injection, remote code execution)
• High (H): Serious security vulnerabilities that should be addressed promptly (e.g., authentication bypasses, privilege escalation)
• Medium (M): Moderate security risks that should be addressed in normal development cycles (e.g., weak encryption, input validation issues)
• Low (L): Minor security concerns with limited impact (e.g., information disclosure, weak recommendations)
• Info (I): Informational findings for awareness with minimal security risk (e.g., code quality suggestions, best practice recommendations)

Other Columns:

• Time: Duration taken by each scanner to complete its analysis
• Action: Total number of actionable findings at or above the configured severity threshold that require attention

Scanner Results:

• PASSED: Scanner found no security issues at or above the configured severity threshold - code is clean for this scanner
• FAILED: Scanner found security vulnerabilities at or above the threshold that require attention and remediation
• MISSING: Scanner could not run because required dependencies/tools are not installed or available
• SKIPPED: Scanner was intentionally disabled or excluded from this scan
• ERROR: Scanner encountered an execution error and could not complete successfully

Severity Thresholds (Thresh Column):

• CRITICAL: Only Critical severity findings cause scanner to fail
• HIGH: High and Critical severity findings cause scanner to fail
• MEDIUM (MED): Medium, High, and Critical severity findings cause scanner to fail
• LOW: Low, Medium, High, and Critical severity findings cause scanner to fail
• ALL: Any finding of any severity level causes scanner to fail

Threshold Source: Values in parentheses indicate where the threshold is configured:

• (g) = global: Set in the global_settings section of ASH configuration
• (c) = config: Set in the individual scanner configuration section
• (s) = scanner: Default threshold built into the scanner itself

Statistics calculation:

• All statistics are calculated from the final aggregated SARIF report
• Suppressed findings are counted separately and do not contribute to actionable findings
• Scanner status is determined by comparing actionable findings to the threshold

Scanner	S	C	H	M	L	I	Time	Action	Result	Thresh
bandit	0	0	0	0	4	0	1.0s	0	PASSED	MED (g)
cdk-nag	0	0	0	0	0	0	6.1s	0	PASSED	MED (g)
cfn-nag	0	0	0	0	0	0	5ms	0	PASSED	MED (g)
checkov	0	0	0	0	0	0	4.9s	0	PASSED	MED (g)
detect-secrets	0	0	0	0	0	0	833ms	0	PASSED	MED (g)
grype	0	0	0	0	0	0	39.8s	0	PASSED	MED (g)
npm-audit	0	0	0	0	0	0	356ms	0	PASSED	MED (g)
opengrep	0	0	0	0	0	0	<1ms	0	SKIPPED	MED (g)
semgrep	0	0	0	0	0	0	<1ms	0	MISSING	MED (g)
syft	0	0	0	0	0	0	1.5s	0	PASSED	MED (g)

[mttanke]

could we have a real architecture diagram here?

[mttanke]

could this be a real flow diagram?