medical-literature-evidence-map

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted external data.
  • Ingestion points: The skill ingests untrusted data through the literatureAbstractsText (pasted text), literatureEvidenceFile (uploaded documents), and literatureSearchLink (external URLs) parameters as defined in references/form-schema.json.
  • Boundary markers: The instructions do not specify any boundary markers or instructions for the model to ignore embedded commands within the processed literature.
  • Capability inventory: The skill utilizes a Python runner (scripts/run.py) that performs network operations to the vendor's API (ai-skills.ai).
  • Sanitization: There is no evidence of sanitization or filtering for malicious instructions within the literature content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:31 AM
Security Audit — agent-trust-hub — medical-literature-evidence-map