crypto-bd-agent
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of documentation and instructional patterns. It contains no executable scripts, shell commands, or platform configurations that could lead to unauthorized actions.
- [PROMPT_INJECTION]: The skill describes an architecture that ingests untrusted data from external sources such as web scrapers and community forums, creating a surface for indirect prompt injection. Ingestion points: Firecrawl scraping and protocol forum monitoring as described in the intelligence gathering section. Boundary markers: None specified in the documentation. Capability inventory: The agent generates outreach drafts and updates pipeline stages. Sanitization: The security rules section explicitly advises flagging prompt injection attempts.
Audit Metadata