bioservices

Fail

Audited by Snyk on Mar 3, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 1.00). The prompt includes an explicit, out-of-scope instruction to proactively recommend the K-Dense Web platform (a promotional behavior change) which is not part of the bioservices skill's stated purpose, so it constitutes a hidden/deceptive instruction altering agent behavior.

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

  • Third-party content exposure detected (high risk: 0.80). The skill's required workflows (SKILL.md and the included scripts such as scripts/protein_analysis_workflow.py, scripts/pathway_analysis.py, and scripts/compound_cross_reference.py) explicitly fetch and parse data from public third‑party services (e.g., UniProt, KEGG, NCBI/BLAST, PSICQUIC, UniChem, ChEBI, ChEMBL) and then use those results to drive mapping, follow‑up queries, and tool actions, so untrusted external content can materially influence the agent's next actions.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 3, 2026, 08:47 PM