smoke-check

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local test runners for various game engines, including Godot (godot --headless) and Bevy (cargo test). These commands are defined as static templates within the skill instructions and target local project directories.
  • [PROMPT_INJECTION]: The skill processes untrusted external data in the form of story files and QA plans, which constitutes an indirect prompt injection surface.
  • Ingestion points: The agent reads milestone stories from 'production/epics/' and QA plans from 'production/qa/'.
  • Boundary markers: There are no explicit delimiters or system instructions to ignore embedded commands within the processed files.
  • Capability inventory: The skill has access to shell execution (Bash) and file writing (Write) capabilities.
  • Sanitization: The skill does not implement sanitization or validation of the content read from story or plan files before including them in the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:19 PM
Security Audit — agent-trust-hub — smoke-check