nemo-gym-blade-analysis

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted rollout trajectories and logs, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: scripts/blade_toolkit.py (processes rollout JSONL records and report markdown files).
  • Boundary markers: The skill relies on natural language instructions for the agent to "read trajectories in order" but does not implement automated delimiters or safety boundaries within the toolkit scripts.
  • Capability inventory: The blade_toolkit.py script performs file system operations (read/write) and data extraction; the agent environment allows shell command execution.
  • Sanitization: The skill provides manual sanitization guidelines in references/cvdp-report-example.md to remove credentials and private data before report generation.
  • [COMMAND_EXECUTION]: The skill uses uv run python to execute the local scripts/blade_toolkit.py script for benchmark validation, fact extraction, and scoring. The script is bundled with the skill and uses standard libraries to process local files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 07:46 AM
Security Audit — agent-trust-hub — nemo-gym-blade-analysis