skills/mukul975/anthropic-cybersecurity-skills/implementing-opa-gatekeeper-for-policy-enforcement/Gen Agent Trust Hub
implementing-opa-gatekeeper-for-policy-enforcement
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches data from a Kubernetes cluster using kubectl to perform audits. This data is controlled by the cluster environment and could be manipulated by an attacker to influence agent output.
- Ingestion points: The scripts retrieve resource definitions and violation statuses from the cluster API.
- Boundary markers: There are no specific delimiters to distinguish cluster-provided content from the agent's instructions.
- Capability inventory: The skill has the ability to execute shell commands and read cluster configurations.
- Sanitization: Retrieved data is processed and reported without explicit sanitization steps.
- [COMMAND_EXECUTION]: The Python scripts scripts/agent.py and scripts/process.py utilize the subprocess module to execute kubectl commands for cluster interaction.
- [EXTERNAL_DOWNLOADS]: The skill downloads OPA Gatekeeper via Helm from open-policy-agent.github.io and clones the official policy library from GitHub. These are recognized as well-known services and trusted sources.
Audit Metadata