Trading Best Practices
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The research workflow (SKILL.md Step 1 and research_latest.sh) directs the agent to perform web searches and process results, creating an ingestion point for untrusted data. 1. Ingestion points: External web search results. 2. Boundary markers: Absent from the provided skill instructions. 3. Capability inventory: The skill documentation references file modification via the /implement workflow (SKILL.md Step 4). 4. Sanitization: No sanitization or validation of the ingested external content is defined.
- [SAFE] (SAFE): No evidence of hardcoded credentials, unauthorized network calls, or malicious command execution was found in the documentation or the helper script.
Audit Metadata