mql5-docs-research
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection because it ingests untrusted data from external URLs.
- Ingestion points: Documentation pages from mql5.com are read into the agent context (SKILL.md).
- Boundary markers: Absent; the instructions do not specify how to separate documentation data from instructions.
- Capability inventory: No file-writing or command-execution capabilities are defined in the skill; it primarily outputs markdown summaries.
- Sanitization: Absent; external content is processed for keyword extraction and summarization without validation.
Audit Metadata