infra-iac-pulumi
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the generation of cloud infrastructure based on user-provided inputs (e.g., configuration values in
DatabaseArgs). While this creates an inherent attack surface for indirect prompt injection where malicious data could influence infrastructure state, the skill mitigates this by enforcing strict security patterns. - Ingestion points: Resource arguments and configuration values processed in
SKILL.mdandexamples/core.md. - Boundary markers: The skill mandates the use of
pulumi.interpolatefor handling output values andConfig.requireSecret()for sensitive data, providing logical separation between data and execution logic. - Capability inventory: The skill possesses extensive capabilities, including creating and destroying cloud resources via the Pulumi engine and Automation API.
- Sanitization: The skill relies on Pulumi's native type safety and provides extensive 'Red Flag' warnings to prevent common implementation errors like plaintext secret storage or invisible resource creation.
Audit Metadata