tv-game-loop

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill executes sed and rg to extract text from src/step.nim. These are standard utilities used appropriately for reading local file content and do not perform destructive actions.
  • PROMPT_INJECTION (LOW): The workflow processes file content, which constitutes an indirect prompt injection surface. 1. Ingestion points: The file src/step.nim is read into the context. 2. Boundary markers: Absent; the workflow lacks delimiters or instructions to ignore embedded instructions. 3. Capability inventory: The skill uses read-only shell commands for file inspection. 4. Sanitization: Absent; file data is passed directly to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 12:31 AM