ai-observability-promptfoo
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill recommends using
npx promptfoo@latestto execute the evaluation framework directly from the package registry. - [COMMAND_EXECUTION]: Support for custom
javascriptandpythonassertion types allows running arbitrary code on the host system to validate model outputs. - [DATA_EXFILTRATION]: Documents the
--shareflag which uploads evaluation results to the promptfoo.dev cloud service for sharing, which may include sensitive prompt or output data. - [PROMPT_INJECTION]: The skill identifies an indirect prompt injection attack surface where untrusted data from LLM outputs is processed by user-defined code. Ingestion points: model
outputinjavascriptorpythonassertions (e.g.,examples/model-graded.md). Boundary markers: None. Capability inventory: Execution of local scripts via assertions. Sanitization: No built-in sanitization for output data before processing by custom logic. - [EXTERNAL_DOWNLOADS]: Fetches the promptfoo package from the npm registry during execution and uses GitHub Actions for CI/CD integration.
Audit Metadata