The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill includes a TypeScript validation script intended to verify system readiness and API connectivity.
The script checkFondoReadiness verifies that the FONDO_API_KEY environment variable is present in the execution environment.
It performs connectivity and integration health checks against official endpoints at https://api.fondo.com/v1.
[INDIRECT_PROMPT_INJECTION]: The skill requires the agent to process external evidence files, creating a potential surface for indirect instructions embedded in those files.
Ingestion points: Instructions in SKILL.md direct the agent to read and grep external files to "Attach evidence" for the checklist.
Boundary markers: The skill provides explicit instructions to "Exclude financial records, tax data, payroll data, and credentials" from the generated launch receipt output.
Capability inventory: The skill is configured with Read and Grep tools and contains code for performing network requests to the Fondo API.
Sanitization: Protection relies on the agent following the negative constraints provided in the instructions; no programmatic validation of external data is performed.

fondo-prod-checklist