ledger
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external, potentially untrusted data such as Infrastructure-as-Code (IaC) definitions and cloud utilization metrics to produce cost optimization recommendations and CI/CD gate configurations. This creates a surface where malicious content embedded in source code or resource metadata could attempt to influence the agent's behavior.
- Ingestion points: Processes Terraform, CloudFormation, and Pulumi code as specified in
SKILL.mdandreference/iac-cost-estimation.md. - Boundary markers: There are no explicit instructions provided to the agent to use delimiters or to disregard natural language instructions that might be embedded within the files being analyzed.
- Capability inventory: The skill generates automated handoffs including IaC deltas (
LEDGER_TO_SCAFFOLD), alert rules (LEDGER_TO_BEACON), and CI/CD thresholds (LEDGER_TO_GEAR). - Sanitization: The instructions do not define specific sanitization or validation logic for content extracted from the analyzed infrastructure files.
Audit Metadata