skills/elfa-ai/skills/elfa-gmx/Gen Agent Trust Hub

elfa-gmx

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a companion skill and documentation hosted on the vendor's official GitHub repository and subdomains (github.com/elfa-ai/skills, docs.elfa.ai, dev.elfa.ai, go.elfa.ai). These are legitimate resources for the elfa-ai platform.
  • [PROMPT_INJECTION]: The skill defines a platform surface for indirect prompt injection with the following evidence: 1. Ingestion points: External social signals and LLM predicates mentioned in the strategy section. 2. Boundary markers: No delimiters or ignore instructions are specified in the provided skill text. 3. Capability inventory: Automated market and limit order execution on GMX. 4. Sanitization: Not detailed in the skill body. This surface is part of the vendor's intended automation functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 07:58 AM
Security Audit — agent-trust-hub — elfa-gmx