Agent Security (Priority: +2.0)

1. Harden CI/CD Pipelines Against PromptPwnd AI Injection | Intermediate Aikido Security disclosed "PromptPwnd" — five Fortune 500 companies confirmed affected by AI agent injection in GitHub Actions.

1. Audit all .github/workflows/ for user-controlled input (github.event.issue.title) passed into AI agent prompts
2. Sanitize untrusted input: SANITIZED_TITLE=$(echo "$TITLE" | tr -cd '[:alnum:] -' | cut -c1-200)
3. Restrict AI agent tool access to read-only in triage/analysis workflows
4. Set minimal permissions: — contents: read, issues: read, never write access to AI agent jobs
5. Add OpenGrep detection rules for untrusted content interpolated into AI prompts Source: Aikido Security

2. Defend Against AI-Augmented Credential Scanning | Intermediate The FortiGate campaign proved basic defense-in-depth defeats AI-augmented attacks — hardened targets were simply skipped.

1. Audit all perimeter devices for exposed management interfaces on ports 443, 8443, 10443, 4443
2. Enforce MFA on ALL admin and VPN access — the campaign succeeded only against single-factor targets
3. Rotate SSL-VPN and admin credentials with 16+ character minimum
4. Segment management interfaces onto dedicated VLANs with IP allowlists
5. Deploy detection for DCSync, pass-the-hash, and Veeam backup server access (ransomware staging indicator) Source: AWS Security Blog

3. Harden AI Coding Tool Supply Chains with OIDC | Advanced The Clinejection attack chain (prompt injection -> token theft -> malicious publish) is now the template. Defend against it.

1. If you installed [redacted]: uninstall cline AND openclaw globally, reinstall latest, rotate ALL credentials
2. Migrate npm publishing from static tokens to OIDC via GitHub Actions (--provenance flag)
3. Run uvx mcp-scan@latest --skills to audit all installed agent skills and MCP servers
4. Generate AI Bill of Materials: snyk aibom to inventory all models, agents, tools, and skills
5. Disable Actions cache consumption in workflows handling publication secrets Source: Snyk Blog

4. Implement Runtime MCP Security | Advanced Production agents need runtime defense — the "guardrail sandwich" pattern with tool call authorization.

1. Input sanitization with trust labeling on ALL data sources (user prompts, RAG, tool responses, MCP descriptions)
2. Tool call authorization: whitelist allowed tool + argument combinations, reject everything else
3. Rate limiting per-session and per-minute on tool calls; flag anomalous patterns
4. Version-locked, digitally signed tool definitions; regular mcp-scan for tool poisoning detection
5. Comprehensive audit trails via OpenTelemetry across all tool invocations Source: Microsoft Security Blog