tooluniverse-protein-structure-retrieval

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection through its ingestion of external scientific data.
  • Ingestion points: Data retrieved from RCSB PDB, PDBe, and AlphaFold, as well as user-provided protein identifiers (SKILL.md).
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to prevent the model from obeying instructions that might be embedded in the retrieved scientific metadata.
  • Capability inventory: Uses the tooluniverse library to perform data fetching and markdown report generation (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the external API responses is mentioned.
  • [SAFE]: The skill does not contain any direct prompt injection attempts, hardcoded credentials, or malicious persistence mechanisms. All external references are to well-known, trusted scientific research domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 04:32 AM