backtest-review

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious commands, obfuscation, or data exfiltration patterns were detected. The skill serves as a checklist for quantitative risk assessment of trading backtests without using external scripts or dangerous tools.- [PROMPT_INJECTION]: The skill processes untrusted external data, such as backtest code and results, which creates a theoretical surface for indirect prompt injection. However, since the skill lacks any capabilities to perform network operations or modify the file system, this risk is negligible.
  • Ingestion points: Backtest code, results, and equity curves (SKILL.md).
  • Boundary markers: Absent; no delimiters are used to wrap untrusted data.
  • Capability inventory: None; the instructions do not use subprocess calls, file-write operations, or network requests.
  • Sanitization: Absent; no validation or escaping of the processed data is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 02:46 AM
Security Audit — agent-trust-hub — backtest-review