etetoolkit

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of the NCBI taxonomy database (300MB) from official NCBI servers to a local cache (/.etetoolkit/taxa.sqlite) when the NCBITaxa class is instantiated for the first time. This is a standard and documented feature of the ETE toolkit used to retrieve taxonomic lineages and scientific names.
  • [COMMAND_EXECUTION]: The skill provides Python scripts (scripts/tree_operations.py and scripts/quick_visualize.py) that serve as command-line wrappers for tree manipulation and visualization. It also includes documentation for installing necessary system-level rendering dependencies (such as PyQt5 and SVG support) using standard package managers like apt-get and brew.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external biological data files, creating a surface for potential indirect prompt injection if those files contain malicious instructions.
  • Ingestion points: Data enters the agent's context through file parsing methods in ete3.Tree, ete3.PhyloTree, and ete3.ClusterTree (e.g., in SKILL.md and scripts/tree_operations.py).
  • Boundary markers: Absent; the toolkit parses standard formats (Newick, NHX, FASTA) where node names or features are treated as data for analysis and visualization.
  • Capability inventory: The skill has the capability to write files to the local system (tree.write, tree.render) and perform network updates for the taxonomy database.
  • Sanitization: Absent; the skill relies on the standard ete3 library parsers for format validation, but does not implement additional filtering for natural language instructions that might be embedded in node metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 06:44 PM