alphagbm-bps-backtest

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and display natural language summary text (in both English and Chinese) returned from the AlphaGBM API. This represents an attack surface where a compromised or malicious API could return instructions intended to influence the agent's downstream behavior.
  • Ingestion points: The summary.en and summary.zh fields in the API response within SKILL.md.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the returned text.
  • Capability inventory: The skill does not request access to any dangerous tools or provide executable scripts that could be leveraged by an injection.
  • Sanitization: No sanitization or validation logic is specified for the external content.
  • [NO_CODE]: The skill does not include any executable scripts, binaries, or package configuration files. It consists entirely of markdown documentation describing parameters and API interaction schemas.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:00 PM
Security Audit — agent-trust-hub — alphagbm-bps-backtest