biopython

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit examples that assign API keys directly in code (e.g., Entrez.api_key = "your_api_key_here"), which encourages embedding secret values verbatim in generated code/commands and thus poses an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's required documentation and workflow (e.g., references/databases.md, references/blast.md, and references/structure.md) explicitly show using Bio.Entrez, NCBIWWW.qblast, and PDBList.retrieve_pdb_file to fetch and parse public NCBI/PubMed/GenBank/PDB records and BLAST results, which the agent is expected to read and use to drive subsequent fetches and decisions, thus exposing it to untrusted third‑party content.