policy-as-code
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements legitimate security enforcement logic using industry-standard tools (OPA, Kyverno, Checkov) to provide guardrails for infrastructure-as-code and container orchestration.- [SAFE]: No suspicious network requests, obfuscated code, or unauthorized data access patterns were detected within the provided scripts or templates.- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted external configuration data, creating a surface for indirect prompt injection.
- Ingestion points: Reads and processes Terraform plan JSON and Kubernetes manifest files (SKILL.md, references/details.md).
- Boundary markers: No explicit boundary markers or 'ignore' instructions are included in the policy snippets; security relies on the parser integrity of the evaluation tools.
- Capability inventory: The skill uses
opa,conftest,checkov, andkyvernoCLI tools to analyze input data (SKILL.md, references/details.md). - Sanitization: No custom sanitization is performed on input data before processing by the security tools.
Audit Metadata