appfolio-cost-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions and code templates for ingesting and processing data from external AppFolio API endpoints.
- Ingestion points: The
fetchWithCachemethod inSKILL.mdis designed to perform network requests to external endpoints and process the resulting JSON data. - Boundary markers: The skill does not define specific delimiters or "ignore instructions" markers to prevent the agent from potentially obeying malicious prompts hidden in the API response data.
- Capability inventory: The skill demonstrates network fetching capabilities and the ability to log warnings to the console based on data state.
- Sanitization: While the documentation recommends caching only minimized and non-sensitive fields, the provided implementation lacks explicit sanitization or validation of the data returned from the remote source.
Audit Metadata