skills/jeremylongshore/tons-of-skills-marketplace/detecting-infrastructure-drift/Gen Agent Trust Hub
detecting-infrastructure-drift
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill utilizes dynamic execution at load time within
SKILL.mdto runlsandterraform version. These commands are used solely to establish the presence of Infrastructure-as-Code files and the Terraform binary, providing necessary context for the agent without performing sensitive operations. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse outputs from external CLI tools such as
terraform planandaws cloudformation detect-stack-drift. - Ingestion points: Command output from infrastructure tools processed in
SKILL.mdandscripts/drift-check.sh. - Boundary markers: Not explicitly defined for tool outputs.
- Capability inventory: Includes file system read/write, and execution of cloud provider CLI tools (
terraform,aws,gcloud,pulumi). - Sanitization: None detected; the agent is expected to interpret raw CLI output to identify discrepancies.
- [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation for Terraform (HashiCorp) and AWS CloudFormation. These references target well-known, trusted service providers for legitimate educational purposes.
Audit Metadata