tooluniverse-hla-immunogenomics

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from multiple external sources including PubMed, UniProt, and IEDB. This data ingestion creates a surface where malicious instructions embedded in scientific abstracts or annotations could theoretically influence agent behavior.
  • Ingestion points: Data is retrieved through tools such as IMGT_get_gene_info, iedb_get_epitope_mhc, UniProt_search, and PubMed_search_articles.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' markers to separate external content from the agent's core task instructions.
  • Capability inventory: The agent has access to Bash for command execution and can generate/run Python scripts.
  • Sanitization: No explicit mention of sanitizing or validating external tool outputs is provided in the skill documentation.
  • [DYNAMIC_EXECUTION]: The skill explicitly directs the agent to generate and execute Python code at runtime to perform computations and statistical analysis.
  • Evidence: The 'COMPUTE, DON'T DESCRIBE' section instructs the agent to 'write and run Python code via Bash' and to 'execute it and report actual results'.
  • Usage: This capability is intended for data processing using libraries such as pandas, scipy, statsmodels, and matplotlib.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:31 AM
Security Audit — agent-trust-hub — tooluniverse-hla-immunogenomics