rlm-gepa
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a legitimate development framework for optimizing AI agent instructions. It includes documentation on best practices for data management and evaluation safety.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
predict-rlmpackage. This is a vendor-provided dependency required for the language model optimization functionality.\n- [PROMPT_INJECTION]: The skill defines a process for optimizing instructions using external datasets, which introduces a surface for indirect prompt injection.\n - Ingestion points: Data is loaded via
load_trainset()andload_valset()in the project implementation.\n - Boundary markers: The skill explicitly guides users to audit data, use deterministic splits, and prevent data leakage.\n
- Capability inventory: The optimized agent executes logic using the
PredictRLMclass and declared tools.\n - Sanitization: The workflow relies on user-led data auditing to ensure the safety of the training and validation sets.
Audit Metadata