rag-eval

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of evaluation logic through local Python scripts.
  • Evidence: Use of uv run --project scripts/eval python scripts/eval/evaluate_rag.py to trigger benchmarks.
  • Context: These commands are used to interact with the project's internal evaluation suite as intended by the skill's primary purpose.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its core function of processing external datasets.
  • Ingestion points: Reads data from the corpus/ directory and the train.json file for RAG indexing and testing.
  • Boundary markers: None identified; the skill relies on standard data processing workflows without explicit delimiter-based isolation.
  • Capability inventory: File system access tools (Read, Write, Edit) and shell execution (uv, python3) are available to the agent to perform the evaluation. It also performs network requests to RAG and ingestor endpoints.
  • Sanitization: No specific content sanitization or validation of the input datasets is documented before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:35 PM
Security Audit — agent-trust-hub — rag-eval