genomic-intelligence

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill provides explicit instructions for secure secret management, advising the use of environment variables for the API key (GI_API_KEY) and warning against hardcoding credentials in code.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's hosted API (api.genomicintelligence.ai, mcp.genomicintelligence.ai) and the public Ensembl genomic database (rest.ensembl.org), which is an established and well-known service in the scientific community.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests DNA sequence data and metadata from external sources and user inputs. The attack surface is limited because the primary data type is non-linguistic genomic code and the skill lacks capabilities for local code execution or file system modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 10:19 AM
Security Audit — agent-trust-hub — genomic-intelligence