backtest-review

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted input data from backtests. Ingestion points: Data reviewed using SKILL.md instructions. Boundary markers: None. Capability inventory: The skill has no file-write, network, or command-execution tools. Sanitization: None.
  • [SAFE]: All components of the skill are purely instructional. No evidence of obfuscation, exfiltration, or persistence was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:41 PM
Security Audit — agent-trust-hub — backtest-review