skills/wu-yc/labclaw/biopython/Gen Agent Trust Hub

biopython

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external biological files and databases, which represents a potential surface for indirect prompt injection.
  • Ingestion points: The skill parses external biological data formats such as FASTA, GenBank, and PDB files using the Bio.SeqIO and Bio.PDB modules, and fetches data from NCBI via Bio.Entrez and Bio.Blast.
  • Boundary markers: The provided documentation and code examples do not include explicit instructions or markers to delimit external data or to warn the agent to ignore instructions embedded within the biological records.
  • Capability inventory: The skill has the capability to perform network requests to NCBI web services and conduct file system operations (reading, writing, and converting sequence files).
  • Sanitization: No mechanisms for sanitizing or validating the content of the biological records are specified before they are processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill installs the biopython library. Biopython is a well-established and reputable open-source project for computational biology.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 05:25 AM