tooluniverse-phylogenetics

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external biological data formats (FASTA, PHYLIP, Newick, etc.) and fetch data from remote genomic databases (NCBI, Ensembl) via ToolUniverse. This creates a potential surface for indirect prompt injection if malicious instructions are embedded within the data files or sequence metadata.
  • Ingestion points: Processes FASTA, PHYLIP, Nexus, and Newick files; fetches data from NCBI, UniProt, and Ensembl.
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: Local file reading, statistical computation (SciPy, NumPy), and remote sequence retrieval.
  • Sanitization: No specific sanitization or validation logic for data content is described in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 05:25 AM