finfocus-routing
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
finfocusCLI tool for configuration management and testing. Examples includefinfocus config routes listandfinfocus config routes test, which are standard operations for the tool's intended purpose. - [INDIRECT_PROMPT_INJECTION]: The skill introduces a data ingestion surface by describing how the agent can process external Pulumi plan JSON files.
- Ingestion points: External Pulumi plan JSON files (
plan.json) processed by thefinfocus costcommand. - Boundary markers: No explicit markers or delimiters are defined to separate untrusted data from instructions.
- Capability inventory: Local shell execution of
finfocusCLI commands as defined in the skill documentation. - Sanitization: The instructions do not specify any validation or sanitization steps for the ingested plan data.
Audit Metadata